Chris Parsons

Describe what you want, and Claude builds the first version. Refine through conversation, inline comments, direct edits, or custom sliders. Export to @canva, as PDF or PPTX, or hand off to Claude Code when the design feels right.

@GergelyOrosz Try: github.com/steipete/gogcli - does everything I need for Claude Code

When is Gmail either exposing an API / MCP to feed email to my agent - to review inbounds, archive unimportat ones, draft responses etc Or when is Google building this? My inbox is getting so much more AI-generated junk coming its way. There should be a better way to deal w it

🍴 @wearecherrypick is an app that finds recipes, plans meals and orders groceries from supermarkets - with an AI twist. Helping 500k+ users eat better, it encourages healthy eating and reduces waste with thousands of AI recipes. Read the full story → goo.gle/4bOveWg

I'm demoing how I'm use Claude Code / AI for writing and thinking this Thursday! Sign up to attend or for the recording: chrismdp.com/webinar

@SW_Help Thanks, very helpful! Thanks for all you’re doing in a difficult situation!

@chrismdp We don't currently have accurate train running information due to the partial line closure, but your next service from London Waterloo will likely be the 21:05 service but delayed. It's currently running fast back to London Waterloo but will be delayed through Wimbledon. ^CW

@SW_Help That’s a long trip - worth waiting for a winchester train from Waterloo now lines have reopened? What time will the first one run?

@chrismdp Hi, travel from Paddington with GWR to Reading, then to Basingstoke then onto Winchester. ^DM

FINAL CALL: "Kill Your Prompts" starts in one hour! Free to join? Sign up: chrismdp.com/webinar All sign ups get full slides and recording (even if you don't make it)

@HammerToe Thanks yes - going for a new angle. More interested in tech founder dynamics than the code itself these days.

@chrismdp Nice :) Very interesting to see how you are evolving your software craftsmanship background into the ai-driven world.

new website (eek): chrismdp.com what do you think?

@dctanner hope it went well today!

Moving house tomorrow, and reminded how wild it is in the UK that we won’t actually legally own our new home until we’re probably standing outside it with everything we own in a van.

You control less of your AI conversation than you think. (Quite proud of this infographic. Didn't do well on LinkedIn. Perhaps X users are more discerning?)

I have recently gone back to Notion after a long break. Why? MCP. Changes everything.

Your AI experiments are failing because you're biasing yourself, and being smart makes it worse. How to prevent it: We all suffer from these biases (and many more): → Anchoring Bias - First AI result skews all evaluation → Availability Heuristic - Recent examples feel more common → Subjective Validation - Personal meaning equals perceived accuracy → Sunk Cost Fallacy - Past investment justifies continued use Intelligence is not a defence against these biases. The only protection is systematic measurement before cognitive biases distort your judgment. Most teams skip this rigour and wonder why their "successful" AI experiments don't scale. I created a one-page evaluation framework (attached) that forces objective measurement. Will you print it out and fill it in? …probably not. But the principles are solid and I’d encourage you to follow them! → Before experimenting: Write specific hypotheses about time savings, quality thresholds, and failure modes → After completion: Track actual time (including hidden costs), measure concrete outcomes, calculate true ROI → Red flags: Making excuses for poor output, spending more time fixing than doing manually, feeling defensive about effectiveness We CANNOT prevent bias entirely, but we can fight against it. It's especially hard with AI, but with proper rigour we be as scientific as we can. Which AI tool will you evaluate properly this week?

@_HooJR @HammerToe yeah I've been trying to evaluate objectively

@HammerToe @chrismdp Opus to plan!

Bitten the bullet and paid for Opus and the Claude Max plan for Claude Code. Jury is out so far: trying to be objective on usage and state hypotheses up front.

you see this kind of reaction is why I use Claude over ChatGPT 😁 (although I'm already missing the per project memory)

Whew: more LinkedIn posts scheduled for the next 3 days. It's exhausting coming up with actually good AI content all the time!

@HammerToe sure although it should all be HTTP stream now right? Remote maintained MCP definitely the way forward

@chrismdp I found wasn't too hard to get a FastMCP-based local server up and running. The main issue was realising that everything moved to SSE, and that using Claude Desktop to access it with the `mcp-remote` wrapper.

Just tried local MCP servers, again. Bleurgh. I'm pretty technical and it took an hour to get one of the most popular ones working at all, and then the results were extremely poor. MCP local is a rabbit hole. Don't bother. Remote, well maintained MCP servers is the way to go.