Principal AI Engineer. I catch agentic AI failures before they cost millions, not after. Evals + agentic systems for regulated enterprise. https://nitter.cf/t.co/wNKtykyGgV
New York, NY
Joined March 2009
- Tweets112K
- Following4.4K
- Followers4.7K
- Likes19.5K
Everyone tests their agents. Few test the handoffs between them.
A peer agent’s output is untrusted input: check type, provenance and permissions before the next agent acts. A2A moves messages. It doesn’t make them trustworthy.
Quorel’s handoff evals are nearly ready.
Mike Legemah retweeted
Should people jump into AI Governance, AI Project Management, AI Product Management, or AI Cloud Engineering without understanding the fundamentals of those fields?
No.
Learn your domain first. Then learn how to apply AI.
AI knowledge alone doesn’t replace domain expertise.
Mike Legemah retweeted
Adding “AI” to your job title doesn’t replace knowing your craft.
AI Governance. AI Project Management. AI Product Management. AI Cloud Engineering.
Learn the fundamentals. Then apply AI.
My latest Substack explains why domain expertise still matters. 👇
careerrehab.substack.com/p/l…
🤖 Made with AI
Most AI evals run after the fact, in a dashboard nobody opens.
Better: an MCP tool the agent calls mid-turn. Deterministic checks first, a judge only for the ambiguous middle, and a verdict (allow, warn, block) before anything ships.
Building this as Quorel. Waitlist soon.
Mike Legemah retweeted
Things companies call a layoff before they call it a layoff:
- A reorganization
- A strategic realignment
- Rightsizing
- A voluntary exit program
- Investing in the future
- An opportunity for growth
- Promoted to customer
In regulated AI, an eval score isn’t a metric. It’s release evidence.
Pin model, prompt, tools and policy versions. Version the eval set. Set thresholds by risk before the run. Classify every miss. Rerun on any change.
If you can’t reproduce it, it’s an opinion.
Mike Legemah retweeted
Please keep learning skills beyond AI. There are many paths into tech, and your expertise doesn’t have to revolve around AI.
A few skills to build:
• SQL and data analysis
• Networking and IT troubleshooting
• Software testing and quality assurance
• Business analysis and process improvement
• Cloud administration
• Cybersecurity
• ServiceNow or Salesforce administration
• Project management
Build practical experience, solve real problems, and show the results on your résumé. AI can complement your skills it doesn’t have to be your entire career.
Mike Legemah retweeted
Job applications asking “May we contact your current employer?"
NO????? I'm trying to leave quietly, not announce my escape.
The career habit that pays off every year: logging your accomplishments logpact.com/blog/the-career-…
5 things before an agent goes to production in a regulated enterprise:
1. Deterministic policy enforcement
2. Audit + observability
3. Evals as release gates
4. Bounded autonomy
5. Lifecycle governance
mleg.tech – at Deer Park, NY
My good sis @KanikaTolver just confirmed what I’ve been telling some people over the last couple of years.
Mike Legemah retweeted
Your review is judged against a rubric.
How many lines of it can you back with evidence?
LogPact's gap analysis shows which competencies have wins logged and which are empty, while there's still time to fix it.
Pro, 14-day trial: logpact.com/?utm_source=x&ut…
Prove a single-agent workflow before you build a multi-agent one.
Every extra agent is another handoff to secure and another failure mode to audit.
If you need several: delegation never grants permissions, and protocol compliance is not trust.
Why do non-US recruiters always think it’s a good idea to call you before they email you a job description? Do they think people are just sitting around doing nothing?
Mike Legemah retweeted
Unpopular opinion: the brag doc is bad advice.
Blank docs need you to remember them. You don't.
Smaller works: 1 win, 1 sentence, 60 sec, every day.
30 days → 30 dated wins. Free challenge starts Oct 26: logpact.com/challenge?utm_so…
