Loading video...

Video Failed to Load

Go Home

We gave Jev 2,029 real phone calls. No transcripts or audio; it never heard a word. Our AI receptionist's calls were reduced to pure structure, meaning turns, tool calls, workflow stages and timing. During the calls, Jev made 38,012 turn-level forecasts at 118 ms median latency, reviewed every call...

muratcan's profile picture

Muratcan Koylan

22,718 subscribers

199,630 views • 1 day ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

holy sh*t. Jev's founder Diogo Almeida dropped a Google Doc on coding agents one of these PDFs has the map everyone needs: where Jev sits in an agent loop ↓ agents do the work, Jev makes the calls, the LLM only writes: 1 → task in: one Noul before anything runs. in scope, or does a human need to see it first? 2 → dispatch: a Choice picks who takes the step (research, write or review). act at 0.85+, everything below goes to review 3 → act: Jev gates the tool call (allow, confirm or block). the LLM only writes the arguments 4 → check: a Score decides what comes back (drop, summary or keep). whatever Jev is unsure of goes to a human 5 → finish: Jev says done above 0.8, then code proves the file actually exists the LLM shows up in 2 of 5 stages. everything else is a typed answer, plain code or a person. don't refactor your agent. hand Jev the one fork it hits most (usually the tool gate or dispatch) and watch 3 numbers for a week: cost per completed task, time per completed task, and how often escalation fired and whether it was right. if escalation never fires, the threshold is too loose and your agent is quietly running unsupervised.
0:18

holy sh*t. Jev's founder Diogo Almeida dropped a Google Doc on coding agents one of these PDFs has the map everyone needs: where Jev sits in an agent loop ↓ agents do the work, Jev makes the calls, the LLM only writes: 1 → task in: one Noul before anything runs. in scope, or does a human need to see it first? 2 → dispatch: a Choice picks who takes the step (research, write or review). act at 0.85+, everything below goes to review 3 → act: Jev gates the tool call (allow, confirm or block). the LLM only writes the arguments 4 → check: a Score decides what comes back (drop, summary or keep). whatever Jev is unsure of goes to a human 5 → finish: Jev says done above 0.8, then code proves the file actually exists the LLM shows up in 2 of 5 stages. everything else is a typed answer, plain code or a person. don't refactor your agent. hand Jev the one fork it hits most (usually the tool gate or dispatch) and watch 3 numbers for a week: cost per completed task, time per completed task, and how often escalation fired and whether it was right. if escalation never fires, the threshold is too loose and your agent is quietly running unsupervised.

Archive

31,914 views • 2 days ago

Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.
0:13

Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.

elvis

15,427 views • 9 days ago

Jev + GrokBot is the best GTM system I've ever built It just made my GTM x200 CHEAPER and x400 FASTER than what 95% of teams are running... setup takes literally 9 minutes: prompt → GrokBot → Jev routes every candidate → GrokBot opens only survivors → campaign step 1 → open TypeSafe AI, create API key (keep it off chat paste) step 2 → tell GrokBot: store TYPESAFE_API_KEY in the secure field step 3 → prompt GrokBot: install typesafe-sdk on Agent Computer + smoke system_one (Choice) step 4 → point it at a target: "read end to end, pull positioning, ICP, every proof point. no copy yet" step 5 → add skill gtm-router: every candidate from X / LinkedIn / YouTube gets 6 typed questions → CHEAP SKIP / OPEN FULL / FLAG KOL step 6 → let Jev rank hook archetypes by viral rate, not by how often people post them - this is where the whole playbook comes from step 7 → GrokBot assembles the KOL shortlist and the 7-day plan - you stay in control of anything irreversible the result: → 3,412 candidates, X, LinkedIn and YouTube. → 15.7 seconds. $0.41. → me doing the same reading: 6h 12m. 8 grok bots brief it, Jev decides, GrokBot executes. no fine-tuning, no embeddings, no vector db - 6 typed questions and a schema. Setup your GrokBot JEV GTM today, then read the article below to learn how to build an agent team with JEV.
0:17

Jev + GrokBot is the best GTM system I've ever built It just made my GTM x200 CHEAPER and x400 FASTER than what 95% of teams are running... setup takes literally 9 minutes: prompt → GrokBot → Jev routes every candidate → GrokBot opens only survivors → campaign step 1 → open TypeSafe AI, create API key (keep it off chat paste) step 2 → tell GrokBot: store TYPESAFE_API_KEY in the secure field step 3 → prompt GrokBot: install typesafe-sdk on Agent Computer + smoke system_one (Choice) step 4 → point it at a target: "read end to end, pull positioning, ICP, every proof point. no copy yet" step 5 → add skill gtm-router: every candidate from X / LinkedIn / YouTube gets 6 typed questions → CHEAP SKIP / OPEN FULL / FLAG KOL step 6 → let Jev rank hook archetypes by viral rate, not by how often people post them - this is where the whole playbook comes from step 7 → GrokBot assembles the KOL shortlist and the 7-day plan - you stay in control of anything irreversible the result: → 3,412 candidates, X, LinkedIn and YouTube. → 15.7 seconds. $0.41. → me doing the same reading: 6h 12m. 8 grok bots brief it, Jev decides, GrokBot executes. no fine-tuning, no embeddings, no vector db - 6 typed questions and a schema. Setup your GrokBot JEV GTM today, then read the article below to learn how to build an agent team with JEV.

Movez

85,453 views • 9 days ago

JEV ENGINEERING JUST CUT A CLAUDE LOOP FROM $765/MONTH TO $3.02 the expensive part isn’t always writing code. a busy overnight loop can burn ~600 decisions just asking what to do next, whether a command is safe, or if the task is finished. trigger → Jev → allow / stop / wake → Claude only builds when needed at roughly 4,000 tokens per decision, those checks can cost ~$25.50 a night on Fable 5.1. Jev handles the same decision layer at $0.042 per 1M input tokens with output free. over 30 nights that moves the decision bill from ~$765 to $3.02. batch multiple questions into one call and it falls again to about $1.08/month. that’s the part i care about: Claude keeps the expensive work that actually needs intelligence, while Jev handles the hundreds of tiny judgment calls around it.
0:15

JEV ENGINEERING JUST CUT A CLAUDE LOOP FROM $765/MONTH TO $3.02 the expensive part isn’t always writing code. a busy overnight loop can burn ~600 decisions just asking what to do next, whether a command is safe, or if the task is finished. trigger → Jev → allow / stop / wake → Claude only builds when needed at roughly 4,000 tokens per decision, those checks can cost ~$25.50 a night on Fable 5.1. Jev handles the same decision layer at $0.042 per 1M input tokens with output free. over 30 nights that moves the decision bill from ~$765 to $3.02. batch multiple questions into one call and it falls again to about $1.08/month. that’s the part i care about: Claude keeps the expensive work that actually needs intelligence, while Jev handles the hundreds of tiny judgment calls around it.

Gipp 🦅

25,010 views • 2 days ago

Jev + SERV is actually insane. We already showed you can increase Jev's performance with SERV Reasoning. Now we're taking it further, bringing Jev-powered Decision nodes into Graph Sharding with the upcoming SERV v3. Here's a breakdown of how it works: Jev is a decision-making model. Given a task and a set of options, it predicts which path is more likely. Think of the octopus that predicted World Cup results. Jev does that for your business, except it's not luck. It weighs every option and tells you how sure it is. It does this by assigning probabilities to outcomes. It doesn't generate text on its own, so you can't expect it to create a new outcome for you. But that's also what enables it to be lightning fast and dirt cheap. For example, in customer service you can ask Jev how to triage an incoming query and route it to the correct department. It can only select from the list of departments you provide it. This also means it can't hallucinate a new outcome outside the options it's given, which makes it incredibly interesting for OpenServ. In Graph Sharding, we take a single system prompt and break it down into multiple LLM steps with deterministic input and output shapes. Some of these steps require an LLM to produce new output, while others are simply decision routers that determine the next possible path. Traditionally, LLMs are slow and expensive. Breaking a single prompt into multiple steps increases accuracy and reliability by a ton, but it also introduces latency. Jev takes on those decision nodes, which are the backbone of a business process and therefore SERV graphs, and makes them super consistent and lightning fast, lowering the overall cost and latency of graph execution. SERV Reasoning on its own is a great force multiplier for Jev because, like all other models, it works by interpreting input instructions. The clearer those instructions are, the better the model performs. That's where SERV Reasoning comes into play. Just like amplifying any other model, we also amplify the accuracy and consistency of Jev's responses. And now we're bringing Jev-powered Decision nodes into Graph Sharding with SERV v3.
0:13

Jev + SERV is actually insane. We already showed you can increase Jev's performance with SERV Reasoning. Now we're taking it further, bringing Jev-powered Decision nodes into Graph Sharding with the upcoming SERV v3. Here's a breakdown of how it works: Jev is a decision-making model. Given a task and a set of options, it predicts which path is more likely. Think of the octopus that predicted World Cup results. Jev does that for your business, except it's not luck. It weighs every option and tells you how sure it is. It does this by assigning probabilities to outcomes. It doesn't generate text on its own, so you can't expect it to create a new outcome for you. But that's also what enables it to be lightning fast and dirt cheap. For example, in customer service you can ask Jev how to triage an incoming query and route it to the correct department. It can only select from the list of departments you provide it. This also means it can't hallucinate a new outcome outside the options it's given, which makes it incredibly interesting for OpenServ. In Graph Sharding, we take a single system prompt and break it down into multiple LLM steps with deterministic input and output shapes. Some of these steps require an LLM to produce new output, while others are simply decision routers that determine the next possible path. Traditionally, LLMs are slow and expensive. Breaking a single prompt into multiple steps increases accuracy and reliability by a ton, but it also introduces latency. Jev takes on those decision nodes, which are the backbone of a business process and therefore SERV graphs, and makes them super consistent and lightning fast, lowering the overall cost and latency of graph execution. SERV Reasoning on its own is a great force multiplier for Jev because, like all other models, it works by interpreting input instructions. The clearer those instructions are, the better the model performs. That's where SERV Reasoning comes into play. Just like amplifying any other model, we also amplify the accuracy and consistency of Jev's responses. And now we're bringing Jev-powered Decision nodes into Graph Sharding with SERV v3.

Armagan Amcalar

365,108 views • 7 days ago

I built HypeMeter in 4 hours with Jev + Minds. Its best trick is saying no, and deciding what is likely a rug vs real hype. I am giving away an Argonaut NFT to reward Beta testers. Yes, that's you. Every "alpha bot" screams BUY. None of them tell you which cheap listings are cheap for a reason. So I wired two things together: Jev by TypeSafe AI . It does not write essays. It answers typed questions: pick one, score this, yes or no. About a third of a second per decision, cheap enough to judge every cheap listing instead of a shortlist. Minds by Minds by Animoca Brands . Your own AI agent. Tell it your strategy in plain words ("Argonauts under 0.3, grade A or better") and it messages you one digest a day, pings you whenever steals are available. First full sweep: 898 listings across 20 collections, including Robinhood (of course). Calls that survived: one. And that one was my own bug: an "83% edge" that was a 2-item bid read as one. The sanity check now kills those before anyone sees them. That is the product. Most cheap NFTs are traps, and it says so. It also hunts rares priced under what their trait actually sells for. Yesterday it flagged an Argonaut with a 1-in-70 palette, listed at 0.79 ETH two days before the same palette sold for 0.9 and 1.0. No hindsight. Every call is written down the moment it is made, then graded at 24 hours and 7 days. Public scoreboard, losses included. Free while in beta. Sign in with Minds: And yes, the giveaway is real: Argonaut #2764 goes to someone who actually uses it. Every active day is an entry, there is a leaderboard, and signing in before 24 Sept gets you 3 bonus entries. Rules on the site. RT and comment "Jev" for extra entry. Have fun sniping.
0:14

I built HypeMeter in 4 hours with Jev + Minds. Its best trick is saying no, and deciding what is likely a rug vs real hype. I am giving away an Argonaut NFT to reward Beta testers. Yes, that's you. Every "alpha bot" screams BUY. None of them tell you which cheap listings are cheap for a reason. So I wired two things together: Jev by TypeSafe AI . It does not write essays. It answers typed questions: pick one, score this, yes or no. About a third of a second per decision, cheap enough to judge every cheap listing instead of a shortlist. Minds by Minds by Animoca Brands . Your own AI agent. Tell it your strategy in plain words ("Argonauts under 0.3, grade A or better") and it messages you one digest a day, pings you whenever steals are available. First full sweep: 898 listings across 20 collections, including Robinhood (of course). Calls that survived: one. And that one was my own bug: an "83% edge" that was a 2-item bid read as one. The sanity check now kills those before anyone sees them. That is the product. Most cheap NFTs are traps, and it says so. It also hunts rares priced under what their trait actually sells for. Yesterday it flagged an Argonaut with a 1-in-70 palette, listed at 0.79 ETH two days before the same palette sold for 0.9 and 1.0. No hindsight. Every call is written down the moment it is made, then graded at 24 hours and 7 days. Public scoreboard, losses included. Free while in beta. Sign in with Minds: And yes, the giveaway is real: Argonaut #2764 goes to someone who actually uses it. Every active day is an entry, there is a leaderboard, and signing in before 24 Sept gets you 3 bonus entries. Rules on the site. RT and comment "Jev" for extra entry. Have fun sniping.

Jesus is Lord | Chev

48,652 views • 8 days ago

Jev + Muse is the first AI agent system that actually automate 100% of my life 99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup just 5 min and setup is ready: prompt → Muse → Jev decision → Muse execution → result step 1 → create your Jev API key (typesafe website) step 2 → clone and install the complete router from Github below python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY' add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions step 5 → test the entire chain, not the raw Jev API: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the final JSON should contain action, reason, mode, jev_used and confidence details step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓
0:16

Jev + Muse is the first AI agent system that actually automate 100% of my life 99% of people pay 200x more for slower AI agents - while 1% run this 2030 setup just 5 min and setup is ready: prompt → Muse → Jev decision → Muse execution → result step 1 → create your Jev API key (typesafe website) step 2 → clone and install the complete router from Github below python3 -m venv .venv && .venv/bin/pip install -r requirements.txt && cp config.example.yaml config.yaml step 3 → export the key before running anything: export TYPESAFE_API_KEY='YOUR_KEY' add the same export to ~/.zshrc or ~/.bashrc if you want it to survive a new terminal session step 4 → give your agent skill/jev-decision-layer.SKILL.md and connect it to src/router.py + recipes/ , raw Jev returns probabilities - the router converts them into executable actions step 5 → test the entire chain, not the raw Jev API: .venv/bin/python -m src.cli '{"goal":"what is 2+2?","kind":"chat"}' the final JSON should contain action, reason, mode, jev_used and confidence details step 6 → keep mode: shadow for 20–50 real decisions: the agent works normally while Jev’s routes are logged and checked; promote only reliable question packs step 7 → switch to mode: active with hard confidence gates: ≥0.80 act automatically, 0.50–0.79 advisory only, <0.50 escalate to the human the result: Jev + Muse is a system that decides what to do, what to skip and when to bring in - I’ve tested it across my daily workflows, and it’s the best setup I’ve found for automating routine Take the exact stack I built, run it yourself from the repo - then read the full Jev architecture behind it ↓

codila

91,306 views • 7 days ago

Top 12 agentic use cases for Jev: (bookmark this) Jev handles semantic decisions that ordinary code cannot express reliably. It returns typed answers and probabilities, while code continues to cover the workflow. Here are 12 practical use cases for Jev: 1. Browser next action > Convert the current DOM state into a bounded action such as click, type, or stop. Code executes only valid operation-target pairs. There are already several open-source Jev web agents. 2. Context compaction > Decide which events from a long agent trace should remain. The selected text stays verbatim instead of being replaced with a generated summary. 3. Skill and context loading > Compare the current user turn against the available skills. Load only the instructions needed for that turn instead of filling the context window with every skill. 4. Typed tool-call compilation > Map a natural-language request to a function and fill its typed arguments. Each argument is evaluated separately before code allows execution. 5. Citation verification > Check whether a quoted passage exists and whether the surrounding evidence supports the claim. The output can be supported, unsupported, or contradicted. 6. Extraction verification > Run a cheap extractor first, then use Jev to verify questionable fields. Clean records stay on the fast path while uncertain ones reach a reasoning model. 7. Agent trace evaluation > Turn raw trajectories into queryable labels such as progress and repetition. This avoids asking another LLM to write a full review of every run. 8. Semantic regression tests > Replay a trace suite against a new agent build. Semantic checks can then pass or block prompt, model, tool, and policy changes in CI. 9. Jevgrep code search > Search a codebase by what the code does rather than its exact words. Jev scores candidate snippets and returns the most relevant code first. 10. Entity alignment > Compare two candidate records and decide whether to merge, review, or keep them separate. Candidate generation remains deterministic while Jev handles semantic identity. 11. Retrieval reranking > Let embeddings retrieve a broad candidate set, then use Jev to reorder passages by relevance. The generation model receives the most useful evidence first. 12. Memory promotion gate > Capture a completed agent trace, then judge whether its corrections contain a reusable lesson. Trace-backed lessons can be promoted while task-specific noise is discarded. If you want to see the final pattern in practice, it is already implemented in the Beacon open-source project. Beacon captures full sessions across Claude Code, Codex, Cursor, OpenCode, and 20+ agent harnesses, and then Jev identifies which workflows and corrections are worth learning from, so that a lesson discovered by one agent can become available to the others. GitHub repo: (don’t forget to star it ⭐) If you want to dive deeper, I also wrote about a similar mechanism in a hands-on guide. It covers building a Jev-style decision path with open models, entirely locally. Read it below.
0:16

Top 12 agentic use cases for Jev: (bookmark this) Jev handles semantic decisions that ordinary code cannot express reliably. It returns typed answers and probabilities, while code continues to cover the workflow. Here are 12 practical use cases for Jev: 1. Browser next action > Convert the current DOM state into a bounded action such as click, type, or stop. Code executes only valid operation-target pairs. There are already several open-source Jev web agents. 2. Context compaction > Decide which events from a long agent trace should remain. The selected text stays verbatim instead of being replaced with a generated summary. 3. Skill and context loading > Compare the current user turn against the available skills. Load only the instructions needed for that turn instead of filling the context window with every skill. 4. Typed tool-call compilation > Map a natural-language request to a function and fill its typed arguments. Each argument is evaluated separately before code allows execution. 5. Citation verification > Check whether a quoted passage exists and whether the surrounding evidence supports the claim. The output can be supported, unsupported, or contradicted. 6. Extraction verification > Run a cheap extractor first, then use Jev to verify questionable fields. Clean records stay on the fast path while uncertain ones reach a reasoning model. 7. Agent trace evaluation > Turn raw trajectories into queryable labels such as progress and repetition. This avoids asking another LLM to write a full review of every run. 8. Semantic regression tests > Replay a trace suite against a new agent build. Semantic checks can then pass or block prompt, model, tool, and policy changes in CI. 9. Jevgrep code search > Search a codebase by what the code does rather than its exact words. Jev scores candidate snippets and returns the most relevant code first. 10. Entity alignment > Compare two candidate records and decide whether to merge, review, or keep them separate. Candidate generation remains deterministic while Jev handles semantic identity. 11. Retrieval reranking > Let embeddings retrieve a broad candidate set, then use Jev to reorder passages by relevance. The generation model receives the most useful evidence first. 12. Memory promotion gate > Capture a completed agent trace, then judge whether its corrections contain a reusable lesson. Trace-backed lessons can be promoted while task-specific noise is discarded. If you want to see the final pattern in practice, it is already implemented in the Beacon open-source project. Beacon captures full sessions across Claude Code, Codex, Cursor, OpenCode, and 20+ agent harnesses, and then Jev identifies which workflows and corrections are worth learning from, so that a lesson discovered by one agent can become available to the others. GitHub repo: (don’t forget to star it ⭐) If you want to dive deeper, I also wrote about a similar mechanism in a hands-on guide. It covers building a Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

122,419 views • 3 days ago

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.
0:19

this is f*cking beyond comprehension. Google engineers just shipped the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.

NO1ennn

24,666 views • 13 days ago

"Yesterday on our way home, we broke down 2 hours away from home... on a busy interstate with three kids in tow. It wasn't exactly ideal, especially with a hungry newborn. I wouldn't get the baby out of his seat to feed him incase we got smacked by another vehicle on the highway, he was the safest in his seat. We called dispatch and AAA and an Alabama State Trooper showed up to help. I thought he was just going to divert traffic away from our lane, but he did so much more than that. He loaded the kids and I in his car and got us off the highway and to the closest rest stop. Sean stayed with the car to wait for the tow truck. He checked the bathroom for 'boogieman so Madeline could use the restroom. He shot illuminating helicopters in the sky with the kids while I made calls to try to get home. Major got really fussy when I was trying to wrangle my other children and calm them down from the evening's happenings. Without hesitation, he took Major out of his seat and gave him the bottle I had prepared from earlier. It seemed like he does that every day, knew how to hold him and when to burp him. Major even filled his pants during his feeding and the trooper laughed and continued feeding him. He then helped unload all our stuff from our car to his and drove our family to the nearest hotel. It was late, nothing was open, and we couldn't get a rental car until the morning. He helped unload our unruly amount of crap into our hotel room, told us where all the rental car places were, gave the girls a hug, and told us to call if we needed anything. That my friends... is humanity." 🙏
0:18

"Yesterday on our way home, we broke down 2 hours away from home... on a busy interstate with three kids in tow. It wasn't exactly ideal, especially with a hungry newborn. I wouldn't get the baby out of his seat to feed him incase we got smacked by another vehicle on the highway, he was the safest in his seat. We called dispatch and AAA and an Alabama State Trooper showed up to help. I thought he was just going to divert traffic away from our lane, but he did so much more than that. He loaded the kids and I in his car and got us off the highway and to the closest rest stop. Sean stayed with the car to wait for the tow truck. He checked the bathroom for 'boogieman so Madeline could use the restroom. He shot illuminating helicopters in the sky with the kids while I made calls to try to get home. Major got really fussy when I was trying to wrangle my other children and calm them down from the evening's happenings. Without hesitation, he took Major out of his seat and gave him the bottle I had prepared from earlier. It seemed like he does that every day, knew how to hold him and when to burp him. Major even filled his pants during his feeding and the trooper laughed and continued feeding him. He then helped unload all our stuff from our car to his and drove our family to the nearest hotel. It was late, nothing was open, and we couldn't get a rental car until the morning. He helped unload our unruly amount of crap into our hotel room, told us where all the rental car places were, gave the girls a hug, and told us to call if we needed anything. That my friends... is humanity." 🙏

G-MA & G-PA

180,601 views • 7 months ago

🚨 SCAM ALERT: Stop. Think. Verify. LVMPD has received numerous calls today from concerned citizens who received scam phone calls that sounded and felt very real. Scammers may claim you: Failed to appear in court Missed jury or grand jury duty Have a warrant for your arrest Must immediately pay money to avoid arrest They may leave a convincing voicemail, using actual names of our officers, or keep you on the phone while pressuring and threatening you. Do not fall for it. Law enforcement will never demand immediate payment over the phone to prevent an arrest. Never provide personal or financial information to someone who calls unexpectedly. Hang up and independently contact LVMPD or your local law enforcement agency to verify the claim. Visit to explore our growing collection of common scams, the tactics scammers use and how to recognize them. STOP. THINK. VERIFY.
0:10

🚨 SCAM ALERT: Stop. Think. Verify. LVMPD has received numerous calls today from concerned citizens who received scam phone calls that sounded and felt very real. Scammers may claim you: Failed to appear in court Missed jury or grand jury duty Have a warrant for your arrest Must immediately pay money to avoid arrest They may leave a convincing voicemail, using actual names of our officers, or keep you on the phone while pressuring and threatening you. Do not fall for it. Law enforcement will never demand immediate payment over the phone to prevent an arrest. Never provide personal or financial information to someone who calls unexpectedly. Hang up and independently contact LVMPD or your local law enforcement agency to verify the claim. Visit to explore our growing collection of common scams, the tactics scammers use and how to recognize them. STOP. THINK. VERIFY.

LVMPD

52,115 views • 2 months ago

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.
0:14

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

John Turner

21,029 views • 12 days ago

🚨 BREAKING: Secretary of State of Marco Rubio has just stunned the world, launching a plan to DESTROY the International Criminal Court (ICC) threats to American sovereignty Marco just confirmed it: NO GLOBALIST JUDGE HAS ANY AUTHORITY OVER AMERICANS, "international law" has NO EFFECT in the USA 🇺🇸 "As we speak, the ICC and its friends are waging a war against our country, not with bullets or missiles, but with statutes and compacts and the force of so-called international law!" "They believe that they should be in charge of YOUR laws, of YOUR country, YOUR life, and they don't care whether or not you agree." "Halfway across the world, there's an institution that calls itself the International Criminal Court. Maybe you've heard of it, maybe you haven't. The chances are you don't know the names of its judges, of its prosecutors, or its president!" "It was a global tribunal staffed by unelected globalist bureaucrats who claimed their power is almost unlimited. The danger of this global court has only continued to grow." "It threatens every aspect of our political and legal system. Border Patrol agents removing violent criminals from our country, American Marines risking their lives to defend our homeland, prosecutors working to dismantle terrorist plots to attack and kill Americans." "If we stand idle, all of them would be at the mercy of foreign judges thousands of miles away facing the constant risk of prosecution and even imprisonment for the so-called crime of defending their own country." "The American people never agreed to any of this, and they never will. Read the words of our Declaration of Independence. We fought a revolution against a foreign power transporting us beyond seas to be tried for pretended offenses!" "Independence is our birthright. We will never let foreign bureaucrats take that away from us. This administration will not sit by as the ICC and its allies seek to threaten our people." "If they believe they can deprive us of our sovereignty, we will teach them the full meaning of American resolve." BASED.
0:19

🚨 BREAKING: Secretary of State of Marco Rubio has just stunned the world, launching a plan to DESTROY the International Criminal Court (ICC) threats to American sovereignty Marco just confirmed it: NO GLOBALIST JUDGE HAS ANY AUTHORITY OVER AMERICANS, "international law" has NO EFFECT in the USA 🇺🇸 "As we speak, the ICC and its friends are waging a war against our country, not with bullets or missiles, but with statutes and compacts and the force of so-called international law!" "They believe that they should be in charge of YOUR laws, of YOUR country, YOUR life, and they don't care whether or not you agree." "Halfway across the world, there's an institution that calls itself the International Criminal Court. Maybe you've heard of it, maybe you haven't. The chances are you don't know the names of its judges, of its prosecutors, or its president!" "It was a global tribunal staffed by unelected globalist bureaucrats who claimed their power is almost unlimited. The danger of this global court has only continued to grow." "It threatens every aspect of our political and legal system. Border Patrol agents removing violent criminals from our country, American Marines risking their lives to defend our homeland, prosecutors working to dismantle terrorist plots to attack and kill Americans." "If we stand idle, all of them would be at the mercy of foreign judges thousands of miles away facing the constant risk of prosecution and even imprisonment for the so-called crime of defending their own country." "The American people never agreed to any of this, and they never will. Read the words of our Declaration of Independence. We fought a revolution against a foreign power transporting us beyond seas to be tried for pretended offenses!" "Independence is our birthright. We will never let foreign bureaucrats take that away from us. This administration will not sit by as the ICC and its allies seek to threaten our people." "If they believe they can deprive us of our sovereignty, we will teach them the full meaning of American resolve." BASED.

Eric Daugherty

2,757,245 views • 2 months ago

after consistently booking 100 b2b calls/mo from linkedin inbound funnels... i sat down with Lara Acosta and gave away our ENTIRE playbook in a 1-hour interview → every system → every framework → every DM script for context, a post with 40 comments booked me 4 qualified calls last week a single question in the DMs booked a client 72 calls in 26 days and one lead magnet batch generated 7,000 comments across 4 variations in this interview i break down exactly how all of it works... here's what's inside: → why i think content pillars are dead and what replaced them (awareness stage positioning: problem unaware, pain aware, solution aware) → the lead magnet system we run at 100 per week across all client accounts (what makes a good one, why 50 pages of text is a waste, and why the best lead magnets right now are all Claude/AI related) → the DM conversion framework that turns a free resource into a booked call in 3-5 messages ("hey, what caught your attention?" → discover the pain → drop a case study → assume the yes with a specific date and time) → why engagement doesn't equal revenue and what actually does (30k followers with low engagement booking 10x more calls than before because the conversion infrastructure changed) → the trend jacking strategy that makes dead accounts go viral overnight (spot it on X in the morning, build the resource by noon, post on linkedin by evening) → how to get your first case study using pay-for-results instead of free trials → the competitor analysis shortcut for never running out of content ideas → why the linkedin algorithm conversation is 90% excuse and 10% useful like + comment "POD" and i'll send you the full interview (must be following + RT for priority access)
0:15

after consistently booking 100 b2b calls/mo from linkedin inbound funnels... i sat down with Lara Acosta and gave away our ENTIRE playbook in a 1-hour interview → every system → every framework → every DM script for context, a post with 40 comments booked me 4 qualified calls last week a single question in the DMs booked a client 72 calls in 26 days and one lead magnet batch generated 7,000 comments across 4 variations in this interview i break down exactly how all of it works... here's what's inside: → why i think content pillars are dead and what replaced them (awareness stage positioning: problem unaware, pain aware, solution aware) → the lead magnet system we run at 100 per week across all client accounts (what makes a good one, why 50 pages of text is a waste, and why the best lead magnets right now are all Claude/AI related) → the DM conversion framework that turns a free resource into a booked call in 3-5 messages ("hey, what caught your attention?" → discover the pain → drop a case study → assume the yes with a specific date and time) → why engagement doesn't equal revenue and what actually does (30k followers with low engagement booking 10x more calls than before because the conversion infrastructure changed) → the trend jacking strategy that makes dead accounts go viral overnight (spot it on X in the morning, build the resource by noon, post on linkedin by evening) → how to get your first case study using pay-for-results instead of free trials → the competitor analysis shortcut for never running out of content ideas → why the linkedin algorithm conversation is 90% excuse and 10% useful like + comment "POD" and i'll send you the full interview (must be following + RT for priority access)

paolo trivellato

23,381 views • 3 months ago

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.
0:15

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Milk Road AI

70,655 views • 6 months ago

Watching this Sears footage hit different if you actually grew up in those aisles. That wasn’t just a store. For a lot of us in the 70s and 80s it was the catalog that came in the mail, the Wish Book you circled until the pages wore thin, Craftsman tools that outlived the first house you bought them for, Kenmore appliances that didn’t need replacing every four years, and a place your parents could walk in and walk out with school clothes, a washing machine, and a socket set in one trip. Sears didn’t invent American middle-class life, but it packaged it. Quality you could point to. A catalog you could trust when you lived nowhere near a big city. Saturday mornings that smelled like floor wax and new denim. Christmas lists that felt possible. What we lost wasn’t only a retailer. We lost the habit of buying something once and expecting it to last. We lost the shared ritual of flipping those pages with a sibling and arguing over who got the last circle. We lost a store that treated a $12 wrench and a $400 refrigerator with the same seriousness. I still catch myself telling the grandkids, “This used to last.” They look at me like I’m speaking another language. Maybe that’s the real story in the video. Not that Sears was perfect. It wasn’t. But for a stretch of years it taught a whole country that “good enough to last” was a normal standard. If you remember the catalog, the orange Craftsman box, or standing in that checkout line with a parent who actually knew the salesperson’s name — you didn’t just shop there. You grew up there. What do you still have in the garage or kitchen that came from Sears and still works? #Sears #1970s #ChildhoodMemories
0:15

Watching this Sears footage hit different if you actually grew up in those aisles. That wasn’t just a store. For a lot of us in the 70s and 80s it was the catalog that came in the mail, the Wish Book you circled until the pages wore thin, Craftsman tools that outlived the first house you bought them for, Kenmore appliances that didn’t need replacing every four years, and a place your parents could walk in and walk out with school clothes, a washing machine, and a socket set in one trip. Sears didn’t invent American middle-class life, but it packaged it. Quality you could point to. A catalog you could trust when you lived nowhere near a big city. Saturday mornings that smelled like floor wax and new denim. Christmas lists that felt possible. What we lost wasn’t only a retailer. We lost the habit of buying something once and expecting it to last. We lost the shared ritual of flipping those pages with a sibling and arguing over who got the last circle. We lost a store that treated a $12 wrench and a $400 refrigerator with the same seriousness. I still catch myself telling the grandkids, “This used to last.” They look at me like I’m speaking another language. Maybe that’s the real story in the video. Not that Sears was perfect. It wasn’t. But for a stretch of years it taught a whole country that “good enough to last” was a normal standard. If you remember the catalog, the orange Craftsman box, or standing in that checkout line with a parent who actually knew the salesperson’s name — you didn’t just shop there. You grew up there. What do you still have in the garage or kitchen that came from Sears and still works? #Sears #1970s #ChildhoodMemories

NancyH

15,281 views • 10 days ago

I’m still riding the high from today. The Tulsa Oilers Jewish Heritage Game was incredible. It was one of those rare moments that makes you feel like you’re watching the American promise actually happen in real time. Because what happened in that arena was simple, and it was enormous. We lived openly and proudly as Jews. In public. In our city. With joy. With confidence. With thousands of our neighbors cheering alongside us. There are moments lately when Jews are reminded, sometimes subtly, sometimes not, that we’re “supposed” to keep it down. Don’t be too visible. Don’t be too proud. Don’t ask for too much. Today was the opposite of that. Today was: we’re here. Today was: we belong. Today was: we’re proud. I looked around that arena and felt my chest tighten from emotion. That blue jersey with the Magen David. And we didn’t just have a fun night, we made history. This is the first time Jewish Heritage Game jerseys have been worn in a professional sports game. Think about that. In Tulsa. In 2026. With a packed arena. With our neighbors joining in. With Jewish pride celebrated. And what moved me most was this. It wasn’t only Jews wearing it. So many of our non-Jewish neighbors wore it too. If you’re Jewish, you know that’s not just “nice.” That’s deeply meaningful. The Magen David carries memory. It carries history. It carries everything our people have walked through. To see it worn proudly, by people who simply wanted to say, “We’re with you. You belong here,” was a kind of decency that restores your faith in people. That’s Tulsa. And it’s also America at its best. A country where you don’t have to erase yourself to belong, where identity isn’t a liability, where you can be fully who you are and still be fully part of the “we.” I’m proud of Jewish Tulsa. Proud of how our community showed up, joyful, confident, unafraid to celebrate who we are. And I’m proud of this city. Proud of the Tulsa Oilers organization for doing this with excellence and heart. Proud of Tulsa for showing up and making it real. Our identity is something we receive, carry, and hand to our kids stronger than we found it. Today that felt real and tangible. So yes, the game was incredible. But what I’ll remember is the feeling. Proud to be Jews. Proud to be Americans. Proud to be Tulsans. A huge thank you to Michael A. Sachs for the vision and heart that went into making this possible. Yasher Koach brother! And a heartfelt thank you to the Tulsa Oilers Hockey club for helping Jewish Tulsa celebrate this community and our city.
0:13

I’m still riding the high from today. The Tulsa Oilers Jewish Heritage Game was incredible. It was one of those rare moments that makes you feel like you’re watching the American promise actually happen in real time. Because what happened in that arena was simple, and it was enormous. We lived openly and proudly as Jews. In public. In our city. With joy. With confidence. With thousands of our neighbors cheering alongside us. There are moments lately when Jews are reminded, sometimes subtly, sometimes not, that we’re “supposed” to keep it down. Don’t be too visible. Don’t be too proud. Don’t ask for too much. Today was the opposite of that. Today was: we’re here. Today was: we belong. Today was: we’re proud. I looked around that arena and felt my chest tighten from emotion. That blue jersey with the Magen David. And we didn’t just have a fun night, we made history. This is the first time Jewish Heritage Game jerseys have been worn in a professional sports game. Think about that. In Tulsa. In 2026. With a packed arena. With our neighbors joining in. With Jewish pride celebrated. And what moved me most was this. It wasn’t only Jews wearing it. So many of our non-Jewish neighbors wore it too. If you’re Jewish, you know that’s not just “nice.” That’s deeply meaningful. The Magen David carries memory. It carries history. It carries everything our people have walked through. To see it worn proudly, by people who simply wanted to say, “We’re with you. You belong here,” was a kind of decency that restores your faith in people. That’s Tulsa. And it’s also America at its best. A country where you don’t have to erase yourself to belong, where identity isn’t a liability, where you can be fully who you are and still be fully part of the “we.” I’m proud of Jewish Tulsa. Proud of how our community showed up, joyful, confident, unafraid to celebrate who we are. And I’m proud of this city. Proud of the Tulsa Oilers organization for doing this with excellence and heart. Proud of Tulsa for showing up and making it real. Our identity is something we receive, carry, and hand to our kids stronger than we found it. Today that felt real and tangible. So yes, the game was incredible. But what I’ll remember is the feeling. Proud to be Jews. Proud to be Americans. Proud to be Tulsans. A huge thank you to Michael A. Sachs for the vision and heart that went into making this possible. Yasher Koach brother! And a heartfelt thank you to the Tulsa Oilers Hockey club for helping Jewish Tulsa celebrate this community and our city.

Joe Roberts

27,554 views • 7 months ago

Regarding the Eric Trump / Daniel Cormier “text scandal”, I am open to being convinced otherwise, but I do not believe for one second that Eric Trump would text something so stupid to Daniel Cormier. It’s laughably stupid on its face to think that Eric Trump would ask a UFC commentator if any of the fights are “rigged”. That he would ask it in writing. And that he would not, for example, just pick up the phone and call Dana White or Joe Rogan himself. That said, I just want to understand what happened. Daniel Cormier said he was hacked. Is that to say he was hacked at the text level, or the X post level? Did he in fact make the post, and delete it? If he made the post, did he do it as a joke to illustrate how absurd the text hack was, but realized how the post could be misinterpreted as real? Or did someone make the post from his X account he subsequently deleted it. I know there are some who are going to say he made the post in earnest, thinking the text messages were real, intending to call out the “corruption”, and he has since been threatened, deleted the post, and claimed “hack”, etc. I can tell you exactly why I do not believe, even if he made the post, he did it believing the text message was real, intending to call out the “corruption”. If Cormier seriously thought the text messages were real, he would understand that by posting it publicly, it would literally destroy the UFC, his livelihood and his legacy - in addition to the legacy of everyone who has ever competed in the UFC. There is no realm of the universe in which even if it were in fact a real text that he actually received from Eric Trump, he would post it publicly. Because it would mean the end of the UFC. I just want to know if he actually made the post from his X account, or if the entire post was the result of a hack (hence the subsequent deleting of the post). Serious and sincere questions for clarity that would benefit everyone Eric Trump
0:16

Regarding the Eric Trump / Daniel Cormier “text scandal”, I am open to being convinced otherwise, but I do not believe for one second that Eric Trump would text something so stupid to Daniel Cormier. It’s laughably stupid on its face to think that Eric Trump would ask a UFC commentator if any of the fights are “rigged”. That he would ask it in writing. And that he would not, for example, just pick up the phone and call Dana White or Joe Rogan himself. That said, I just want to understand what happened. Daniel Cormier said he was hacked. Is that to say he was hacked at the text level, or the X post level? Did he in fact make the post, and delete it? If he made the post, did he do it as a joke to illustrate how absurd the text hack was, but realized how the post could be misinterpreted as real? Or did someone make the post from his X account he subsequently deleted it. I know there are some who are going to say he made the post in earnest, thinking the text messages were real, intending to call out the “corruption”, and he has since been threatened, deleted the post, and claimed “hack”, etc. I can tell you exactly why I do not believe, even if he made the post, he did it believing the text message was real, intending to call out the “corruption”. If Cormier seriously thought the text messages were real, he would understand that by posting it publicly, it would literally destroy the UFC, his livelihood and his legacy - in addition to the legacy of everyone who has ever competed in the UFC. There is no realm of the universe in which even if it were in fact a real text that he actually received from Eric Trump, he would post it publicly. Because it would mean the end of the UFC. I just want to know if he actually made the post from his X account, or if the entire post was the result of a hack (hence the subsequent deleting of the post). Serious and sincere questions for clarity that would benefit everyone Eric Trump

Viva Frei

30,167 views • 3 months ago

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.
0:17

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.

Anam Hira

42,149 views • 2 months ago

EXCLUSIVE from Patrick Maguire on our podcast The State of It: * Sir Keir Starmer’s relationship with Ed Miliband has broken down to such an extent that the energy secretary has been accused of “ghosting” the prime minister in recent weeks * Senior government sources claimed that Miliband declined to take calls from the prime minister during a tense stand-off over defence spending * No 10 became increasingly concerned last week that Miliband could quit over the imposition of cuts on his department to fund defence spending * The State of It, the political podcast by The Times and The Sunday Times, has been told that Starmer attempted to contact Miliband repeatedly but did not receive a response. He was said to have been “ghosted” * This account was rejected by a source close to Miliband, who said that the pair did eventually speak and denied that Miliband declined to take the prime minister’s calls * Multiple sources said that Starmer and Miliband were barely on speaking terms and that the prime minister was “furious” at what he regarded as the energy secretary’s “betrayal” * Lara Spirit reveals that several cabinet ministers are weighing up whether to resign after the by-election in an attempt to force Starmer’s hand. Allies of Burnham suggested that Miliband was likely to be among them * The prime minister is said to have become increasingly “entrenched” as he prepares to fight any challenge from Burnham. Starmer sees himself as a “servant of the country rather than the party” and allies said he was determined to resist a “coronation” * An ally of Starmer said: ‘“It would be coup territory, it would profoundly undemocratic. We don’t really know what Burnham stands for or what he would do. Winning a by-election is very different to running the country. Win or lose, someone has to flush out his positions. Keir is becoming more entrenched’
0:14

EXCLUSIVE from Patrick Maguire on our podcast The State of It: * Sir Keir Starmer’s relationship with Ed Miliband has broken down to such an extent that the energy secretary has been accused of “ghosting” the prime minister in recent weeks * Senior government sources claimed that Miliband declined to take calls from the prime minister during a tense stand-off over defence spending * No 10 became increasingly concerned last week that Miliband could quit over the imposition of cuts on his department to fund defence spending * The State of It, the political podcast by The Times and The Sunday Times, has been told that Starmer attempted to contact Miliband repeatedly but did not receive a response. He was said to have been “ghosted” * This account was rejected by a source close to Miliband, who said that the pair did eventually speak and denied that Miliband declined to take the prime minister’s calls * Multiple sources said that Starmer and Miliband were barely on speaking terms and that the prime minister was “furious” at what he regarded as the energy secretary’s “betrayal” * Lara Spirit reveals that several cabinet ministers are weighing up whether to resign after the by-election in an attempt to force Starmer’s hand. Allies of Burnham suggested that Miliband was likely to be among them * The prime minister is said to have become increasingly “entrenched” as he prepares to fight any challenge from Burnham. Starmer sees himself as a “servant of the country rather than the party” and allies said he was determined to resist a “coronation” * An ally of Starmer said: ‘“It would be coup territory, it would profoundly undemocratic. We don’t really know what Burnham stands for or what he would do. Winning a by-election is very different to running the country. Win or lose, someone has to flush out his positions. Keir is becoming more entrenched’

Steven Swinford

56,610 views • 3 months ago