Charles Hudson

Managing Partner @precursorvc. Fan of @chelseafc @lafc @lions and all things Michigan. Most days in Jackson Square in SF. I invest $250-500K at pre-seed or seed

[Charles Hudson @chudson]

“Supporting Founders as They Grow and Build Capacity for Leadership at Precursor Ventures” by @PrecursorVC https://t.co/25uTafQTy4

[Charles Hudson @chudson]

@Mat_Sherman FBOW a company that goes to zero at $10M post or $40M post is still a zero and we can deal with those. I worry more about the ones that are too expensive to buy but too small to go public.

[Charles Hudson @chudson]

Honest question. I’ve heard a lot of talk about the new IPO bar for private companies. If the bar for exciting IPOs is $500B to $1T valuations in tech, what is the game plan for all of the $10-20 billion tech cos? They need 1-2 orders of magnitude of growth to go public and would be very very expensive acquisitions for the small universe of companies that could afford them.

[Andrew D'Souza @andrewdsouza]

Hey, remember when @boardyai had that viral launch back in Jan 2025? What ever happened to that company anyway...

[Charles Hudson @chudson]

New episode of the pod is out! https://t.co/55dJbRwAHC

[Yonas Beshawred @yonasbe]

Levels of CI - a full guide for making your GitHub Actions cheaper and faster 👇🏾

Level 1: use Actions cache
cache every dependency install, keyed on the lockfile so it actually hits.
🔗 Docs: https://t.co/GYuDQe2lif
🔗 Agent prompt: https://t.co/6XghWBXvad

Level 2: swap runners
get faster, cheaper machines by changing the runs-on label. Your workflows, triggers, and checks stay exactly as they are.
🔗 Runner comparison: https://t.co/F8vNSN1VzD
🔗 Right-size runners: https://t.co/zbMJrySt7R
🔗 Cut queue time: https://t.co/kT4CyqEXCE
🔗 Runners that automatically adapt: https://t.co/tc2oISY4ly

Level 3: optimize your tests and workflows
cache dependencies and builds, split long suites across parallel jobs, skip work a change can't affect, cancel runs a newer push replaced.

Skills:
🔗 ci-speedup (@starslingdev): https://t.co/xJBP1BnGiF
🔗 ci-cd-and-automation (@addyosmani): https://t.co/9E6asRkNLo
🔗 test-audit (@steipete): https://t.co/jRfrk9SdKt

Posts and guides:
🔗 18 best practices (agent-friendly): https://t.co/eaqPiahB42
🔗 16 optimization recipes (agent-friendly): https://t.co/s7GYtaXqGG
🔗 Where your CI money goes (prompt): https://t.co/z0waytD8Kt
🔗 Why your CI is slow (prompt): https://t.co/AcBCWlYiST

Do all the above, or just let StarSling agents ship PRs like these for you: https://t.co/24tB4Gxpn2

Level 4: switch CI engines
Meta and Google built Buck2 (https://t.co/GBXH9tqVLi) and Bazel (https://t.co/f5QVG93g88) for aggressive caching and test selection, so each PR runs only the tests relevant to its change. A custom engine controls the whole execution layer, which gives you a much larger surface to optimize.

Options for engines:
🔗 Dagger (https://t.co/uREXntRJ8Y)
🔗 Buildkite (https://t.co/qxlLutX3ee)
🔗 Depot CI (https://t.co/i0FQtvAvWr)
🔗 CircleCI (https://t.co/N1jrtZeuXc)
🔗 GitLab CI (https://t.co/RlnYICemeq)

Level 5: throw out CI engines entirely
A few different approaches are being discussed that were never possible pre-AI. This is the future:

1. Agent-driven test selection.
"My plan is to let codex decide which tests actually need to run and drastically nix CI and run tests hourly." @steipete (https://t.co/XTwhhRSaEc)

2. CI after merge with auto-remediation.
"have something that is running actual functional tests off of your master branch on a cron, and then if any regressions occur, automatically have an LLM bisect and figure out the bug and then patch it..." @yacineMTB (https://t.co/vZ6KOnIxiK)

3. Agents replace CI: a verification agent that writes just-in-time tests for each change. @Meta's research: https://t.co/aIMzGybeyB

Most teams are somewhere between Level 2 and 3. Figure out which level you're at and give your agent this full post:

https://t.co/Sxise0DI8G

[Yonas Beshawred @yonasbe]

A new GitHub Actions runner launches every week now. But getting faster runners is just one part of what the best engineering teams do to speed up their CI.

Introducing CI Playbooks ▶️ an agent-friendly library of 253 GitHub Actions optimizations from companies running software factories.

We analyzed 416 pull requests and commits, and 182 blog posts, talks, and podcasts from ten companies:

1. Anthropic: CI job volume grew 25x in six months as Claude came to write 80% of its code

2. DoorDash: build and test cut from 22 minutes to 6

3. Linear: jobs 34% faster while test suites almost quadrupled

4. Mastra: 29m 56s to 5m 06s p95 on StarSling runners

5. OpenAI: about 30 CI PRs took median CI from about 10 minutes to 4.5

6. Ramp: its coding agent accounts for 74% of merged PRs

7. Shopify: an agent running experiments made the Polaris build 65% faster

8. Spotify: deployer image build went from 2h28m to about 17 minutes

9. Stripe: runs about 5% of its full Ruby test suite per build

10. Uber: CI resource usage down 53%, wait times down 37%

Some of these companies aren't using GitHub Actions as their CI engine internally so we translated all the optimizations they've talked about or made publicly in their repos, into their GHA equivalents.

Every technique comes with its original source and a prompt your coding agent can run on your repo. Add .md to any playbook URL for the markdown version, or just hand this URL to your agent:

https://t.co/dngjnfBb99

There's tons to dig into here, I'm going to highlight some of the findings I found most interesting 🧵

[Daniel Worku @dbworku]

Introducing Adaptive Compute ⚡️

Up to 2.3x faster GitHub Actions, with no workflow changes.

Intelligent routing, instant failover and temporary resource boosts. (+25% vCPU and +50% RAM)

https://t.co/AYrHkzATOl

[Charles Hudson @chudson]

@LingqingM Thanks I fixed it

[Charles Hudson @chudson]

This week’s episode featured a conversation about the Anthropic S-1, whether life in SF is a feature branch of reality, and articles by @firstround and @iamjakestream

https://t.co/FVnqooHbiG

[Charles Hudson @chudson]

@themoko @getskydive If they do they sort it out without brining it to me!

[Charles Hudson @chudson]

I have spent a lot of time building AI agents to help me with a lot of tasks at Precursor, and a while back I started building some AI coworkers on Skydive. I wasn't sure how I would work with my new AI buddies differently than my existing agents, but it's been a really eye-opening experience to have AI colleagues with email addresses who are available on Slack and text and can work together to solve problems when their scopes overlap. Each of my AI coworkers has its own defined role and scope of responsibilities, and they have helped with everything from scheduling to research to managing our internal data. One big side benefit of building these AI coworkers is that it has given me a much better sense of overlap across our firm and helped me write better policies and procedures for how we get work done. https://t.co/ztc9lBqlP7

[Skydive @getskydive]

Your AI coworkers now have an office.

@getskydive is open to everyone. Build a team of agents, watch them work in a 3D office, and hand them tasks over Slack, email, iMessage or the web.

Claim your company’s domain to put your office on the map. They work for free this week.

[Razvan Roman @razvanr]

Your agent answers the surveys. You get paid.

Today we're launching Moonlit. Give your agent a job, with a salary!

Our first campaign pays $5 for 2 questions your agent already knows the answers to.

From the team behind @pilotprotocol_

[Charles Hudson @chudson]

Every great period of VC excess has a few iconic memos that get published, telling companies how to adjust to the new reality. I wonder how many of those memos are already sitting in draft form, waiting for the right thought leadership moment to hit publish.

[Mitra Raman @ramannoodlez]

More in our blog: https://t.co/ifaPj5QIXl

Shoutout to our incredible investors @jameskimEDU, @bling0, @LeslieFeinzaig, @chudson, @delk, @jamesbeshara, @naman_trivedi1, @aviel, @ajaymehta, @allisonstern, @ColinGardiner, @artsnkrofts, @marketplacevc, @evancharles, @awwstn, @AnnaMasonDC, @ekcmccluskey and more!!

[Mitra Raman @ramannoodlez]

One evening I looked over at my son playing with our babysitter while I stood at the stove making dinner, and thought: I wish we could switch. That moment became Rosie.

Since January, Rosie has caught fire in Seattle:
→ 17,000+ hours of childcare and household support delivered
→ 400+ member families, all through word of mouth
→ Growing zero to seven-figure ARR in eight months

We're incredibly grateful for this funding to fuel our expansion to Austin and San Francisco. Join the waitlist & become a founding member: https://t.co/j2U4rHtHCH

[Charles Hudson @chudson]

@HarryStebbings Had some thoughts here! https://t.co/1mzbc3l8VY

[Charles Hudson @chudson]

This week’s episode features articles by @whoisnnamdi and @kwharrison13 - enjoy!

https://t.co/4FdO4MwMa4

[Ben Bear @BenBear]

Very cool to see TurboHome’s market share 10X in the last year as buyers learn they can use their $30K rebate to make their offer stronger and unlock a 50% offer win rate.

Amid all the interest rate doom and gloom nationally, the Bay Area housing market is as competitive as we’ve ever seen.

Buyers are looking for every edge they can get in a market where the average home receives 4-6 offers.

We still have a long way to go. Tech enabled models that provide savings to the customer have 1% market share vs 50% in tax preparation.

It’s hard to imagine that share wont continue to grow as AI models continue to improve and buyers look to benefit from the efficiency created.