Principal AI Engineer. I catch agentic AI failures before they cost millions, not after. Evals + agentic systems for regulated enterprise. https://xitter.cf/t.co/wNKtykyGgV
New York, NY
Joined March 2009
- Tweets112K
- Following4.4K
- Followers4.7K
- Likes19.5K
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…
LLM judge: "summary is grounded." 5-line script: "the claim ID it cites doesn't exist."
Believe the script.
Deterministic checks first. Judge for the rest, validated against human labels. Evals are release gates, not QA.
An agent's identity is not the identity of the person who asked.
Agent runs on a broad service account, user has limited access, agent fetches what the user can't see. Confused deputy.
Propagate the user's context. Authorize server-side at the resource, every time.
Don't give an agent one autonomy level for every task.
L1 read-only L2 reversible prep, human commits L3 controlled execution, approval + checks L4 high-impact, qualified human decides
Bind approvals to exact parameters. Change one, re-approve.
The accuracy lol
The people you'll meet on every interview panel:
- The Hiring Manager: decided in the first 5 minutes, still asks 45 minutes of questions
- The Peer: quietly worried you'll be better than him
- The Skip-Level: joins 10 minutes late, asks "Why this company?" and drops for another call
- The Culture Interviewer: no rubric, no notes, somehow has veto power
- The Shadow: in training, says nothing, still gets a vote
- The One Who Actually Read Your Resume: rare. If you get one, they're usually the reason you get the offer.
