AI Architect & Engineer | Salesforce & AWS Cloud ☁️ | Startups | Healthcare, Legal Tech & EdTech | AI & ML | Family & Fun | Football ⚽️ Tennis 🎾 | MVP & CTO
Joined February 2009
- Tweets 11,231
- Following 773
- Followers 3,800
- Likes 4,169
422 Photos and videos
Pinned Tweet
Jan 2
Four human skills that matter more than ever:
→ Critical thinking
→ First-principles thinking
→ Judgment
→ Taste
And you already have them.
open.substack.com/pub/agentg…
2
2
309
Mike Gill retweeted
The June edition of the Salesforce Architect Digest is packed with 🆕 resources:
📝 Community Author Program blog submissions
🤖 Salesforce Headless 360 architecture insights
🌟 Agentblazer Spotlight
💻 Technical content on Agentforce and Slack
🗓️ Upcoming livestreams and events
Read the latest edition and subscribe for monthly updates. sforce.co/43Iv9OF
2
4
229
Mike Gill retweeted
May 29
The teams seeing the biggest wins from AI are completely changing how they work, not speeding up what they already do. What steps can you delete, what handoffs go away, what can an agent just own end to end. Great to see Salesforce go this deep. Shoutout to Srini, @Benioff & team.
Full writeup: salesforce.com/news/stories/…
35
45
570
88,047
May 14
Love this
May 13
Authoring code by hand HAS GONE AWAY.
Engineering module structure and architecture has not.
86
Mike Gill retweeted
Mar 24
Almost every SaaS app inside Vercel has now been replaced with a generated app or agent interface, deployed on Vercel.
Support, sales, marketing, PM, HR, dataviz, even design and video workflows. It’s shocking.
The SaaSpocalypse is both understated and overstated. Over because the key systems of record and storage are still there (Salesforce, Snowflake, etc.)
Understated because the software we are generating is more beautiful, personalized, and crucially, fits our business problems better.
We struggled for years to represent the health of a Vercel customer properly inside Salesforce. Too much data (trillions of consumption data points), the ontology of Vercel was a mismatch to the built-in assumptions, and the resulting UI was bizarre. We generated what we needed instead. When you don’t need a UI, you just ask an agent with natural language.
We’ve also been moving off legacy systems with poor, slow, outdated, and inconsistent APIs, as well as just dropping abstraction down to more traditional databases. UI is a function 𝑓 of data (always has been), and that 𝑓 is increasingly becoming the LLM.
258
135
1,958
848,227
Mar 11
UK AI is very much alive
Mar 11
15 weird London AI companies you've probably never heard of
London's AI scene isn't just chatbots and SaaS.
Some genuinely strange stuff happening.
@PrimaMente – building "foundation models for the brain" to study Alzheimer's and Parkinson's.
Hologen – frontier medical AI spinout tied to UCL/King's. Eric Schmidt involved. hologen.ai
@baseimmune – AI-designed vaccines targeting rapidly mutating viruses.
@RecursionPharma / @valence_ai – AI drug discovery platform combining chemistry, biology and machine learning.
@CausalyAI – AI that reads scientific papers and maps biomedical knowledge graphs.
Fractile – building new AI chip architecture. fractile.ai
@mindgard – "red teaming" AI models to find vulnerabilities.
@Limbic_ai – mental health triage AI used in NHS services.
@LindusHealth – clinical trials run with AI infrastructure.
Anima Health – AI triage platform for healthcare providers. animahealth.com
AUAR – robots that build buildings. AI for automated construction. auar.io
@testudoglobal – insurance for the AI economy.
Isomorphic Labs – DeepMind spinout doing AI drug discovery. isomorphiclabs.com
BenevolentAI – one of the earliest AI drug discovery companies. benevolent.com
London AI ecosystem is weirder than people think.
Still mapping more.
Comment any i've missed so far.
londonmaxxxing.com/
1
102
Mike Gill retweeted
Feb 23
I've published the first two chapters of a new guide to Agentic Engineering Patterns - coding practices and patterns to help get the best results out of coding agents like Claude Code and OpenAI Codex simonwillison.net/2026/Feb/2…
101
319
2,738
221,736
Mike Gill retweeted
Feb 6
9 Key AI Concepts Explained in 7 minutes
- Tokenization
- Text Decoding
- Prompt Engineering
- Multi Step AI Agents
- RAGs
- RLHF
- VAE
- Diffusion Models
- LoRA
16
233
1,210
98,400
AI agents are the new coworkers. But who's making sure they play by the rules?
Yesterday at Workato's AI Research Lab in SF, we dove into the security challenge of the decade: governing AI that acts autonomously.
We covered:
✅ Why AI agents need different security than traditional software
✅ How to govern systems that make their own decisions
✅ Building trust when agents work alongside humans
✅ How MCP changes the security game
✅ What the future of AI governance looks like
Big thanks to everyone who joined us for brilliant conversation, great food, and even better company!
#AI #AIAgents #MCP
2
5
293
Mike Gill retweeted
Jan 27
I'm keeping two Claude windows open. One making changes to the source code. The other helping me to plan future changes. This uses my time better since I spend a lot less time waiting for Claude to finish.
The two Claudes are in two different directories, both have git repos of the project. The planning directory has rules that prevent source code changes. Only planning is allowed. I manually pull and push changes between the two.
136
102
2,008
575,488
Mike Gill retweeted
Jan 27
You can now customize your Claude Code keybindings!
/keybindings to get started
99
110
1,726
156,586
Jan 28
Interesting
Jan 27
You can now use Claude Code Max with AI Gateway.
Use your existing subscription with Claude Code, and fallback to other providers when you reach your plan's limits or for better reliability.
vercel.com/changelog/claude-…
1
58
Jan 28
Solid move
Jan 27
We’re partnering with the UK's Department for Science, Innovation and Technology to build an AI assistant for GOV.UK.
It will offer tailored advice to help British people navigate government services.
Read more about our partnership: anthropic.com/news/gov-UK-pa…
1
47
Jan 27
How long before Anthropic shut down claude setup-token for Clawdbot? Yesterday was a fast return to sluggish Claude code - oh they have
1
160
Jan 26
Evolution
Jan 26
💯 @ Spec-driven development
It's the limit of imperative -> declarative transition, basically being declarative entirely.
Relatedly my mind was recently blown by dbreunig.com/2026/01/08/a-so… , extreme and early but inspiring example.
53
Mike Gill retweeted
Jan 19
This work by @cursor_ai is, I think, the coolest AI breakthrough since GPT-4. (And there are plenty of candidates!)
simonwillison.net/2026/Jan/1…
69
229
2,938
339,756
Mike Gill retweeted
Jan 15
Rules, commands, MCP servers, subagents, modes, hooks, skills...
There's a lot of stuff! And tbh it's a little confusing.
Here's what you need to know (and how we got here).
116
346
3,735
447,805
Mike Gill retweeted
Jan 14
Curated list of research papers on agentic AI for healthcare
github.com/AgenticHealthAI/A…
26
177
1,191
72,470