Matt Pocock profile photo

Matt Pocock @mattpocockuk on X (Twitter): stats, voice and strategy

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.

Hook formulas, weaknesses and how to get their attention. Included in the free trial, then from $29 a month. See pricing

Followers
382.8K
Following
812
Posts on X
37.5K
Engagement rate
1.15%
Posts a day
2.82
Reply share
0%

Counts as of ; averages from @mattpocockuk's last 200 posts. Engagement rate is likes, reposts and replies divided by views, averaged per post. View @mattpocockuk on X

@mattpocockuk is The Educator

Teaches what they know, one thread at a time.

  • Threads that teach
  • Questions that pull
  • Repeatable frameworks

One of six archetypes Xpert reads from the published numbers: topics, cadence, reply habits and format mix. It is a heuristic label, not one Matt Pocock chose.

How @mattpocockuk's posts perform

An average @mattpocockuk post gets 1.4K likes, 86 replies and 58 reposts from 145K views.

Per post, on average

Likes
1.4K
Reposts
58
Replies
86
Views
145K
Median length
176 chars
Posts analyzed
200

Format mix

With media
25%
With links
24%
Ask a question
16%
Part of a thread
0%

Share of @mattpocockuk's last 200 posts. Replies make up 0% of their output.

When does @mattpocockuk post?

@mattpocockuk posts about 2.8 times a day, most often on Thursdays and between 09:00 and 12:00 UTC. Engagement is heating up: 1.05% across the older half of recent posts, 1.25% across the newer half.

Posts by day of week
Sun: 15 posts, Mon: 36 posts, Tue: 23 posts, Wed: 29 posts, Thu: 42 posts, Fri: 35 posts, Sat: 20 posts
Posts by hour (UTC)
00-03: 1 posts, 03-06: 2 posts, 06-09: 24 posts, 09-12: 54 posts, 12-15: 43 posts, 15-18: 35 posts, 18-21: 37 posts, 21-24: 4 posts
Engagement trend

Heating up

1.05% to 1.25% (+0.2 pts, up)

Oldest half of recent posts against the newest half.

The busiest day and window are in amber. Hours are UTC.

What does @mattpocockuk post about?

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

AI summary of their voice

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,…

What they post about

Agentic Workflows
45%
TypeScript & Frontend Architecture
20%
Software Engineering Education
20%
Developer Productivity/Tooling
15%

Words they lean on

  • agent×59 uses
  • agents×42 uses
  • software×39 uses
  • code×36 uses
  • skill×35 uses

What works for @mattpocockuk

The 'Hard Truth' Reality Check

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

One of 4 patterns. The rest are in the full analysis.

From one of their posts
That's a recipe for a slop cannon. No serious organisation is going to trust a factory like that.

@mattpocockuk's top recent posts

The most-liked of their last 200 posts, with the numbers X reported. Each opens the original.

Matt Pocock

@mattpocockuk ·

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.

134 replies397 reposts5.9K likes658.6K views

What the full analysis adds

The full analysis of @mattpocockuk goes past the public numbers: the hooks they rely on, the patterns that work, the weaknesses holding the account back, and how to get their attention.

The rest of @mattpocockuk's analysis

  • 6 opening-hook formulas, as reusable templates
  • 3 more what-works patterns with real quotes
  • 3 weaknesses holding the account back
  • How to get their attention: what to reply to, in what tone
  • 6 more top posts plus cadence detail
Unlock the full analysis

Included in the free trial, then from $29 a month. Card required, cancel anytime.

The blurred text is a placeholder, not @mattpocockuk's analysis. The real one stays on our server until you unlock it.

Matt Pocock (@mattpocockuk) X (Twitter) Stats, Archetype & Strategy | Xpert