The Whiteboard Guy and Factory Foreman @warpdotdev
Ordering more markers
Joined September 2018
- Tweets15.6K
- Following1K
- Followers48.9K
- Likes37K
Pinned Tweet
We made a skill for assessing the risk of merging a PR: /merge-risk
This addresses the code review bottleneck by helping devs trust the agent for lower risk changes.
It grades risk across 5 categories: alignment, impact, verification, rollback cost, and error detection.
- Alignment: does code follow the PR description and related tickets?
- Impact: what is the blast radius, and does it touch sensitive code paths?
- Verification: does the change include end-to-end verification? This means computer use, screen recordings, before/after screenshots... going beyond unit test coverage.
- Rollback cost: once it's shipped, how trivial is it to revert? @mattpocockuk calls this a "two-way door" vs. a "one-way door."
- Error detection: are errors reported, logged, or simply swallowed?
Try it out:
> npx skills add warpdotdev/common-skills --skill merge-risk
There's a balance flip going on with software factories:
Before: I ping an agent, we work together
After: Agent finds what to do, then it pings me with questions
It's the right direction for managing human attention as we scale up the volume of tasks
You should focus on adjusting code architecture and skills to make agents perform better, yes.
But what's more important is having metrics to track that those adjustments are working!
These could be quantitative (we use cost-per-PR), or qualitative (LLM-as-a-judge scoring).
At Warp, we are having fun tweaking our model mix and factory workflow to drive our cost per PR down. It’s gone from $80 → $20 using a factory approach, with a lower revert rate and 40% higher PR throughput than in the last month.
Folks on the team are suggesting experiments to improve further, like reducing subagents and building model routers. As a startup founder who cares deeply about efficiency and burn, seeing us reduce costs while increasing velocity and quality is incredible.
ALT Line graph shows cost per PR trending downward from mid-September to mid-October. It shows a peak at $80 in aggregate across compute, platform, and inference costs, and a lower total of $20 at the far right of the graph.
Ben Holmes retweeted
At Warp, we are having fun tweaking our model mix and factory workflow to drive our cost per PR down. It’s gone from $80 → $20 using a factory approach, with a lower revert rate and 40% higher PR throughput than in the last month.
Folks on the team are suggesting experiments to improve further, like reducing subagents and building model routers. As a startup founder who cares deeply about efficiency and burn, seeing us reduce costs while increasing velocity and quality is incredible.
ALT Line graph shows cost per PR trending downward from mid-September to mid-October. It shows a peak at $80 in aggregate across compute, platform, and inference costs, and a lower total of $20 at the far right of the graph.
This is a really great article. To start, we should be adding some version of this to every PR description: "Testing", "Risk," and "How to revert."
"Testing" should include static checks and end-to-end verification from the agent. Screen recordings with computer use are the holy grail.
"Risk" should encompass both the depth of the change (i.e. is it a copy change or a deeper system change?) and the sensitivity of the change (i.e. does it touch mission-critical backend or PII?). Anthropic uses a low - medium - high ranking.
"How to revert" should be a playbook for incident response. If a revert wouldn't be easy, consider how it could be!
All of these serve to make code review faster, and to make bouncing back from incidents easier.
Ben Holmes retweeted
💻 Code Engineering: From Coding Agents to Software Factories
Excited to have our next event in San Francisco 🌁 on coding engineering tomorrow (27th October). Don't miss out the chance to learn from the innovative agent labs and learn more about the coding agents and software factories..
🎙️ Amazing Speakers
@sethkarten - @PrimeIntellect
@BHolmesDev - @warpdotdev
@sydneyrunkle - @LangChain
@AndreyRisuka - @FactoryAI
We are about to hit the limit but still some spaces available
👉 RSVP Now: luma.com/cico2dxy
Ben Holmes retweeted
On Friday, we became aware of what we believe to be an active and narrow-banded exploitation of a vendor in Warp's infrastructure. We detected the operation within hours and were able to remediate and mitigate the impact. We have been in touch with the vendor about the vulnerability.
Everyone who uses Warp places a lot of trust in us and that’s not something we take lightly. I’m very sorry that this incident has occurred.
The attack appears to have come from an agent swarm using a very sophisticated penetration and escalation technique, likely starting with a hole in a vendor dependency, and ultimately accessing a limited amount of agent trace and telemetry data.
We have been working over the weekend and we have notified anyone who we have positively identified as impacted. As of today, we believe an upper bound of roughly 1% of Warp users may have been impacted.
We are working closely with the team at Crowdstrike to do a more extensive and comprehensive investigation and have engaged law enforcement.
Anyone who has been impacted will receive instructions from us on action they need to take. We will continue to post updates as we learn more.
We need better debugging tools for agents. So, we've been building them:
- A timeline to show each subagent handoff, with visibility into each subagent trace.
- Cost breakdown per subagent (both token and compute cost)
- Models used at each handoff. Especially useful with automatic routers
- [testing internally] A tool-by-tool flame graph to identify wasted work
These are built into Warp Factories for you to try!
Ben Holmes retweeted
final edit of our software factories masterclass with @vaibcode and @zachlloydtweets is live! We chatted about:
- software factory building blocks
- a good software factory starts with measurement, then self improvement against those metrics
- turning successful agent runs into evals for testing future models / harnesses / etc
- DORA, why counting lines of code is bad metric, and why counting PRs might be good enough
enjoy!
Ben Holmes retweeted
Want better quality output from your agent? Give it a way to verify its own work.
Love what Warp is doing here: every agent gets a computer and brings back a video of what it did. I do something similar in my workflow - on top of E2E tests, Claude gives me recorded videos + screenshots as part of the evidence work is "done".
My bet is verification becomes one of the most important problems to work on this year.
verification is the biggest bottleneck for coding agents right now according to @addyosmani.
we @warpdotdev have put a lot of thought into building a good computer-use tool for Warp Factories. every agents gets a computer to navigate the apps they built, take screenshots and recordings, and post them back for human review.
3-4mins of activity get edited down to 15 clips stitched together with cursor clicks, mouse animations, and key presses.
we've been able to dramatically cut our time to merge and unlocked faster iteration + review cycles, especially for projects that are hard to mock out locally!
Engineering is now 20% prompting, 80% tuning the agents that execute on the prompts
Position software factories not as a “product,” but as an infra platform upon which everyone is expected to do “factory engineering.”
Factory engineering is work to make internal factories better. That means improving the skills, models, and context that drive engineering throughput. It means encouraging engineers to build automations for their chore work. It means giving them the tools to score and benchmark factory workflows, and empowering them to use agents to build self-improvement loops. It means that everyone owns lowering factory costs and improving factory ROI.
If you use a platform like Warp Factories, all of this tooling comes built-in, but beyond the tooling “factory engineering” is really a mindset.
Stop asking agents for text summaries of a PR. They're capable of so much more:
- Architecture diagrams to visually explain the change. Could be ascii, mermaid, HTML, or animated walkthroughs. /show-me is a great starting point.
- Screen recordings verifying the change end-to-end. Most harnesses can do this now with Chrome DevTools or computer use. Warp Factories will auto-edit video and highlight cursor clicks as well.
- Planning documents when humans were in the loop, checked in as code. This is optional, but a product spec explaining the purpose and expected user flow will a) guide the agent to better screen recording verification, and b) help the reviewer when looking at another engineer's work.
Warp Factories shows all artifacts connected to an agent session to make these easy to find.
I met a team of devs regularly zipping up Claude and Codex sessions from their computers and shipping them to a shared S3 bucket.
Why? Because collecting data on agent convos is that valuable. I think shared cloud sandboxes are the way though to avoid all the zipping 😄
We should stop keeping all of our agent conversations local. They should be stored in a shared place.
This lets you do some powerful things:
- Schedule self-improvement agents to review runs and pull out failure modes worth fixing
- Replay past conversations against different models for benchmarking
I met a team of devs zipping up Claude and Codex sessions from their computers and shipping them to a shared S3 bucket. That's... a start 😄 But really, all agent sessions should happen on a single source (like a cloud runner) so that conversation traces are stored together by default.
It's why Warp Factories uses cloud sandboxes and makes sessions available via API. We also added an inbox view to see which conversations need your attention, which is quite convenient:
Stop reviewing agent PRs without verification! If there isn't a screenshot or screen recording, it's not worth your time.
10x more important than optimizing your CI checks.
verification is the biggest bottleneck for coding agents right now according to @addyosmani.
we @warpdotdev have put a lot of thought into building a good computer-use tool for Warp Factories. every agents gets a computer to navigate the apps they built, take screenshots and recordings, and post them back for human review.
3-4mins of activity get edited down to 15 clips stitched together with cursor clicks, mouse animations, and key presses.
we've been able to dramatically cut our time to merge and unlocked faster iteration + review cycles, especially for projects that are hard to mock out locally!
We've been running our software factory out of this config format. Calling it "Terraform for agents." I feel like this should become a standard?
Software factories should be configured as code. With Warp, your factory lives in a repo as markdown and YAML files, so your agents, automations, runners, benchmarks, and even custom model routers are all in one place.
Here, I walk through a typical Warp factory config and show how it lays the foundation for self improvement!
It's pretty awesome DX.
We should stop keeping all of our agent conversations local. They should be stored in a shared place.
This lets you do some powerful things:
- Schedule self-improvement agents to review runs and pull out failure modes worth fixing
- Replay past conversations against different models for benchmarking
I met a team of devs zipping up Claude and Codex sessions from their computers and shipping them to a shared S3 bucket. That's... a start 😄 But really, all agent sessions should happen on a single source (like a cloud runner) so that conversation traces are stored together by default.
It's why Warp Factories uses cloud sandboxes and makes sessions available via API. We also added an inbox view to see which conversations need your attention, which is quite convenient:
If you're looking for a good factory automation, start here:
Have an agent pick up one idle issue, once per day. Heck, once per week.
And if the PRs are bad, don't pause the automation! Make it better. Add UI verification, set better test guidelines, or add static checks.
Code diffs aren't the only measure of agent quality. Efficiency matters too!
Ex: We found agents spinning their wheels working around problems in our test harness. This silently wasted hundreds of tool calls in aggregate.
I presented a system to detect this at @aiDotEngineer
Ben Holmes retweeted
I think "factory engineering" will be the next skillset that developers focus on.
That means tuning the agent orchestration, the automations, the skills, and everything else driving your agents.
We apply this mindset to our own factory, and we're seeing real results:
Here are a couple samples from our own projects, where we've made /merge-risk into a PR automation.
In the first, /merge-risk flagged a PR with wide-ranging impact and missing e2e verification. The fix was to break into manageable stacked PRs and to include before/after screenshots of the app.
In the second, /merge-risk caught a driveby fix made by the agent that fell outside the PR's scope. Documenting this could make the change low-risk without line-by-line code review.
Curious to fine-tune these dimensions across more PRs. It's open source, so please try it out and share your findings!
github.com/warpdotdev/common…
ALT A high merge risk comment details changes in UI shortcuts, IPC handler, and notes verification, highlighting impacts and rollback considerations.
ALT A comment from a bot details merge risk, alignment, impact, verification, rollback cost, and error detection for a code change.