# Matt Pocock (@mattpocockuk): X (Twitter) creator profile

Matt Pocock (@mattpocockuk) is an X (Twitter) creator with 382.8K followers who posts most about Agentic Workflows. Across their last 200 posts they average a 1.15% engagement rate and 2.82 posts a day, busiest on Thursdays.

Bio on X:

> I teach devs for a living. Author of Total TypeScript and AI Hero. Ex-@vercel. Used to be a voice coach.

Analyzed 2026-11-01 from 200 recent posts. X profile: https://x.com/mattpocockuk

## Archetype

**The Educator**: Teaches what they know, one thread at a time.

Traits: Threads that teach, Questions that pull, Repeatable frameworks. One of six archetypes Xpert derives from topics, cadence, reply habits and format mix; a heuristic label, not one the creator chose.

## Stats

| Metric | Value |
| --- | --- |
| Followers | 382.8K |
| Following | 812 |
| Lifetime posts | 37.5K |
| Avg engagement rate | 1.15% |
| Posts per day | 2.82 |
| Reply share of output | 0% |
| Avg likes per post | 1.4K |
| Avg reposts per post | 58 |
| Avg replies per post | 86 |
| Avg views per post | 145K |
| Median post length | 176 chars |
| Posts with media | 25% |
| Posts with links | 24% |
| Posts asking questions | 16% |
| Posts in threads | 0% |

Engagement rate is likes, reposts and replies divided by views, averaged per post. Counts are as of the analysis date; averages come from the posts analyzed.

## Posting rhythm

Busiest day: Thursday. Busiest window: 09:00-12:00 UTC. Engagement trend: heating up (1.05% older half vs 1.25% newer half).

## Voice

Most often Agentic Workflows (45% of recent posts), then TypeScript & Frontend Architecture (20%), Software Engineering Education (20%) and Developer Productivity/Tooling (15%).

Voice (AI summary): Matt speaks with the direct, authoritative, and slightly irreverent tone of an expert who has spent too much time in the terminal. He leans into technical jargon, uses a sharp, opinionated,…

Words they lean on: agent, agents, software, code, skill

## What works for them

**The 'Hard Truth' Reality Check**

He punctures hype bubbles by focusing on the 'slop' and mess that AI actually creates when left unconstrained.

> That's a recipe for a slop cannon. No serious organisation is going to trust a factory like that.

## Top recent posts

Most-liked of the posts analyzed, with the numbers X reported.

> /show-me is a phenomenal skill
> Makes PR descriptions extremely easy to read
> Basically a toolbox of "nice ways to look at code"
> Nice work, @dexhorthy
> https://t.co/phB1dAPwgG

7.6K likes · 516 reposts · 80 replies · 891.8K views · 1 media
https://x.com/mattpocockuk/status/2095460192871698728

> 1. Oh shit, AI can do my job better than me
> 2. Software engineering is dead!
> 3. I can vibe code as much slop as I want!
> 4. Oh, things are not going well. Fable/Sol/Opus all suuuck
> 5. But what if I constrain the agent? Put it in a straitjacket?
> 6. Oh, the results are pretty good now. How do I go deeper?
> 7. *Orders 12 software engineering books from Amazon*
> 8. Software engineering is alive!

7.6K likes · 472 reposts · 325 replies · 700.3K views
https://x.com/mattpocockuk/status/2107749763789578692

> My top 3 skill makers:
> - @poteto 
> - @dexhorthy
> - @emilkowalski
> Always learn a ton from reading their skills.

7.5K likes · 393 reposts · 115 replies · 733K views
https://x.com/mattpocockuk/status/2105022638368403658

> The next great "language for agents" should be:
> - As fast as Rust
> - As little design space as Go
> - Have the strictest type/verification system ever written
> Bend seems like an interesting first effort

6.3K likes · 220 reposts · 510 replies · 721.1K views
https://x.com/mattpocockuk/status/2114407583167705279

> This is an extremely good watch.
> The things that felt novel/interesting to me:
> 1. Lock down your agents
> Humans tend to like 'sharp knife' abstractions - that are powerful, but you can cut yourself if your use them wrong. Lauren says agents perform much better in extremely locked-down environments. Abstractions are designed so they can't screw up, and lint rules enforce it.
> They built a whole internal framework (Dune) to keep the agent on track.
> That helps optimise agents that don't have a large context window to work productively in your codebase.
> 2. Create verification infrastructure
> To trust the results of any agent, you either need to sit and watch it OR have it provide evidence of its improvement. This has always made sense to me, but Lauren really pushes it hard here:
> - Invest in custom CLI's that let the agent drive the app and measure its performance
> - Make the app "factory ready" from the get-go - i.e. deployable to an environment where the agent can mess about with it
> 3. Feature Maps
> Lauren's software factory (what she calls an 'outer loop') often requires the agent to break down vague bug reports from users and to turn those into potential fixes.
> To aid that, they built a 'feature map' of all the main features in their application, which describe exactly how the app is supposed to function.
> This has become essential for helping the agent navigate the codebase, and figure out quickly how things are supposed to work. It's maintained along with the codebase, and kept in sync via automations.
> This is the kind of documentation I usually warn against. It goes stale quickly and can confuse agents if it's not kept up to date.
> But Lauren's team are using it as critical navigation infrastructure, and it makes it possible for agents to explore faster and better - even on a large codebase. So it sounds like navigation docs like this are worth it if they enable new behavior. 
> Banger talk - watch the whole thing on 2x.

5.9K likes · 397 reposts · 134 replies · 658.6K views
https://x.com/mattpocockuk/status/2103431302527508886

> Prompt of the day:
> /retro read my last 10 coding agent sessions and find ways to make my repo easier to navigate. Find where agents take too long to find relevant information, or rely on out-of-date docs.
> Improving navigability is such an underrated way to save tokens.

5.4K likes · 236 reposts · 146 replies · 379K views
https://x.com/mattpocockuk/status/2105951409887949107

## Related creators

- [Theo - t3.gg (@theo)](https://xpert.so/creators/x/theo/md): 418.3K followers
- [@levelsio](https://xpert.so/creators/x/levelsio/md): 984.2K followers
- [kitze 🛠️ tinkerer.club (@thekitze)](https://xpert.so/creators/x/thekitze/md): 106.1K followers
- [Patrick Collison (@patrickc)](https://xpert.so/creators/x/patrickc/md): 1.8M followers

---

Source: https://xpert.so/creators/x/mattpocockuk
The full analysis (hook formulas, weaknesses, how to get their attention) is part of Xpert Growth, which starts with a 3-day free trial (then from $29 a month).
