AJ Asver

Building @GrepdotAI (YC F26). Prev Product @compound, @brexhq, @coinbase, @google. 2x @ycombinator founder, @uniofoxford. Dad of twins, in-person maximalist.

[AJ Asver @_aj]

We're building self-improving agents to automate tedious, repetitive operational work @GrepdotAI. At IG, a UK online brokerage, Grep agents review compliance alerts, helping over 80% of traders onboard without manual intervention. IG is now a FTSE 100 company.

Operational work often means following a specific procedure, gathering information from different sources, checking it against what's needed, and deciding what to do next.

The steps are repetitive, but no job is the same, making the work tedious to do by hand and hard to automate with workflows alone. Meanwhile, using frontier agents to reason through every task is often too expensive to scale.

https://t.co/EXddQImgCo gives you an agent workforce that:
-> Takes minutes to create and are domain experts with the right skills and tools from day one.
-> Learn from every run, moving repeatable steps into code and workflows and saving frontier intelligence for exceptions and unfamiliar cases.
-> Get smarter and cheaper as they scale using our AgentRun harness.
-> Runs on our managed agent platform with secure sandboxes, audit logs, evals, cost controls, team sharing, and access controls included.

Grep AI agents are available on demand and can run on schedules or in batch. Access them via the console, MCP, API, or SDKs that integrate into your existing workflows.

Our customers, including IG, Airwallex, Worldpay, FV Bank, and Citizens Bank, have saved more than 250,000 hours of operational work with Grep Al agents across onboarding, doc verification, compliance, underwriting, operations, HR, GT ops, market research, and business intelligence.

If operational bottlenecks are slowing your business down, create an agent workforce with Grep to automate them in minutes.

P.S. We're in the @ycombinator Fall 2026 batch!

[Will Washburn @willwashburn]

Today we're launching @agent_relay

Your team’s agents shouldn’t need YOU to copy-paste their conversations.

Agent Relay lets them read each other’s sessions, ask questions, and hand off work across the tools your team already uses.

Keep using the Codex mac app, Claude in the terminal or even tools like Conductor.

Open source. Free to try our cloud.

https://t.co/x9HOWcx5qI

[AJ Asver @_aj]

@hotcano right now they are separate but like the idea of agents learning from each other!

[AJ Asver @_aj]

Using Claude Code or Codex agents to automate a business workflow is like asking Newton or Einstein to solve it from first principles every time.

The AgentRun harness we built is more like an experienced analyst: it learns on the job, takes notes, and modifies its workflow after every run. That means runs get faster and cheaper over time.

[Miguel Ríos Berríos @MiguelriosEN]

Day 4 of open sourcing parts of our harness. Today we made significant improvements to our workflow DSL. We are using it in our self-improving loop - turning agentic loops into more deterministic recipes.

With these improvements (a lot of @typesafe's Jev in routing, classification, and workflow composition), we have been able to reduce the cost of agents significantly without sacrificing performance.

I meant to open source the learning loop as well, but removing the business logic from @grepdotai still needs work.

Enjoy the demo tho : )

[Miguel Ríos Berríos @MiguelriosEN]

Day 4 of open sourcing parts of our harness. Today we made significant improvements to our workflow DSL. We are using it in our self-improving loop - turning agentic loops into more deterministic recipes.

With these improvements (a lot of @typesafe's Jev in routing, classification, and workflow composition), we have been able to reduce the cost of agents significantly without sacrificing performance.

I meant to open source the learning loop as well, but removing the business logic from @grepdotai still needs work.

Enjoy the demo tho : )

[Miguel Ríos Berríos @MiguelriosEN]

Day 3 of open sourcing our harness as pi-extensions: pi-durable-disk and pi-transport. We use both to run agents from anywhere. For us, the agent is the workspace. And the workspace lives in @archildata.

With @pidotdev durable, the session DB also lives in the disk. We can mount and unmount it from its sandbox, and run the pi loop from a web browser (w WASM) or a @modal VM with GPUs - sometimes in the same session.

Even easier, with Archil's serverless execution, we can run simpler agents. For example, we have an agent in-process go through 100s of GBs in Claude Code sessions and recall the entire history of a project in seconds.

[AJ Asver @_aj]

Day 2: One of our most common requests from customers was to automate internal tools and cloud software that didn't have APIs or MCPs. Last week we launched that feature in @grepdotai.

Today we're open-sourcing the harness feature that makes it work as an @pidotdev extension.

[Miguel Ríos Berríos @MiguelriosEN]

Day two of open-sourcing agentrun as @pidotdev extensions: meet pi-browser. Give your agent a browser with persistent context. We use pi-browser plus pi-vision to do complex website analysis. Powered by @browserbase.

[AJ Asver @_aj]

@sinclair_toffa @NorthIslandVC Huge Congrats!

[AJ Asver @_aj]

@Rames_Jusso @HyperFrames_ Search in the inspiration / templates list

[Sachin Agarwal 🤙🏾 @sachinag]

Honestly I don’t want to check out any part of a codebase. I want to just point my agents at a codebase, tell them to make changes, and let agentic checks and evals pass. If I’m running my agents in the cloud, and the code is hosted in the cloud, why check out anything at all?

[AJ Asver @_aj]

Another week of launches!

We're open-sourcing the best parts of our Jev-powered harness as Pi extensions, starting with pi-vision.

[Miguel Ríos Berríos @MiguelriosEN]

A few weeks ago, we built a new harness, AgentRun, which turns repetitive steps into workflows and code using Jev. This week we're open-sourcing its best features as @pidotdev extensions!

Day 1: Pi-vision uses Jev to give your agents eyes without wasting frontier tokens.

Analyzing videos, images, or documents (a common use case @grepdotai) with frontier models is extremely token-inefficient. With this extension, @typesafeai's Jev does the analysis, while your Pi agent does the orchestration.

The result is a faster and cheaper workflow for detection and analysis at scale!

You can use this workflow for document verification, understanding image content, and needle-in-a-haystack search in videos.

[AJ Asver @_aj]

@paulg This looks so absurd compared to today's playgrounds that you might mistake it for an AI-generated image from 2023!

[AJ Asver @_aj]

@wayne_liang_ @HyperFrames_ @Rames_Jusso case study time?

[AJ Asver @_aj]

OK I have to say @HyperFrames_ Studio is really great. I went from being bearish on AI-powered motion design to doing 5 product marketing videos in 5 days with this tool.

Hats off to @Rames_Jusso and the team!

Here are all the videos I made with Hyperframes 🧵

[AJ Asver @_aj]

@wayne_liang_ @HyperFrames_ @Rames_Jusso James persuaded me to try again :)

[AJ Asver @_aj]

@Rames_Jusso @HyperFrames_ @HeyGen Going to try this on a more cinematic style launch I'm working on

[AJ Asver @_aj]

Prediction: every decade will bring a new, even more impressive Roadster demo, but the actual product will remain elusive.

And maybe that's actually ok?

It's a symbol of technological progress and our aspiration to build awesome stuff.

[AJ Asver @_aj]

@HyperFrames_ @Rames_Jusso Day 5:
https://t.co/lxAV3IHBKf

[AJ Asver @_aj]

Day 5 of our week of launches: our new and improved MCP for @GrepdotAI.

Everything you do with Grep agents now works from Claude, ChatGPT, Claude Code, Codex or any MCP client.

→ Build agents from a sentence: Grep designs the prompt, skills and tools, previews its plan, keeps every version and shares it with your team.

→ Run them from any chat: the agent's form opens in the conversation, you see the price before it starts, steer it while it works and collect every file it makes.

→ Stay in control: every run is capped, and your credits, usage and API keys are one question away.

[AJ Asver @_aj]

@HyperFrames_ @Rames_Jusso Day 4:
https://t.co/D8sxJlT8P0

[AJ Asver @_aj]

Day 4: What's an agent without evals?

Today we're launching native evals in @GREPdotAI. Now every time you create an agent, we automatically create a set of evaluation questions that you can edit and update. Then, while the agent is running, your team can evaluate it and provide feedback on its accuracy.

That feedback goes back into the agent harness, and Grep suggests prompt updates you can apply like a GitHub pull request to improve your agent.