Samuel Johnson's Work | ContraWork by Samuel Johnson
Samuel Johnson

Samuel Johnson

AI agentic Engineer and automation expert

    3
    Followers
Followed by Odymma E, GALLERY L, and Olafusi T

Lagos, Nigeria

WorkPostsAbout

Lagos, Nigeria

AI agents are confidently wrong. So I made mine check each other's work. Last week I gave 13 agents one job: research crop-disease apps for smallholder farmers. 39 sources, 16 findings. Before anything reached the final report: ā†’ every claim was traced to a page the agent actually opened ā†’ a verifier re-read the riskiest pages against the real text ā†’ 3 independent passes voted, and only repeat findings survived ā†’ a critic tried to prove each gap was already solved What came out: 5 unsolved opportunities and one concrete experiment to run first. It all runs on free-tier AI, and it's open source: github.com/Samthnalyst1234/Farmbt Question for the automation folks here: how do you stop your agents from making things up? Human review, a second model, or something else? šŸ‘‡
0
56
I just finished building my own open-source farm bot called Farmbt šŸŒ± It's a team of 13 AI agents. I asked them one question, and they came back with a ranked list of opportunities nobody has fully cracked yet. You describe a problem area in plain words, and the agents take it from there: šŸ”Ž Researchers search the web in parallel and pull out findings, each with its source āœ… A verifier re-opens the pages and checks every claim against the real text šŸ—³ļø A gap hunter runs three independent passes, and only gaps that show up repeatedly survive šŸ„Š A critic tries to prove each gap is already solved šŸ› ļø Solver agents design fixes, check them against existing products and papers, and write an experiment plan The hard part wasn't getting AI to produce answers. It was making it not make things up. So every claim is graded by evidence, confidence ratings are capped by what the source actually supports, and everything is saved, so a run that hits a rate limit picks up where it stopped. It runs on free-tier models today and gets better with every model upgrade, with no code changes. First test: crop-disease detection apps for smallholder farmers. 39 sources, 16 findings and 5 opportunities, ending in a concrete first experiment to run. Open source: github.com/Samthnalyst1234/Farmbt (https://farmbtgitrepo) If you need an AI pipeline that's reliable enough to trust, for research, automation or anything in between, let's talk šŸ‘‹
2
2
314
Cover image for Another late night. Building a
Another late night. Building a quant trading system an agentic model where different AI agents handle research, testing and risk, and none of them is allowed to place a trade on its own. The hardest part so far? Being honest when the results say "not yet." Most strategies I've tested failed once real costs were included. That's exactly what testing is for. Keeping The Psychology of Money and The Diary of a CEO close while I figure it out. What are you reading these days? #QuantTrading (https://web.facebook.com/hashtag/quanttrading?__cft__[0]=AZgkO2m3tWjeIYVQtrW1jYz-ciuphO-zGjm9gVKGk4f2vsTTraxReWYehX2nb-v-ZARrZN_8X0vP7GRxjUiW0_Oeqtn6Aq8kufxBbW58KIWnSXRQGNj6QsBJapY1qfM0PBS-hifRALgKxOiELPr0mXfEuFEjOLN8brUzi_oIildPSjHkhenc5fPpkcM&__tn__=*NK-R) #AlgoTrading (https://web.facebook.com/hashtag/algotrading?__cft__[0]=AZgkO2m3tWjeIYVQtrW1jYz-ciuphO-zGjm9gVKGk4f2vsTTraxReWYehX2nb-v-ZARrZN_8X0vP7GRxjUiW0_Oeqtn6Aq8kufxBbW58KIWnSXRQGNj6QsBJapY1qfM0PBS-hifRALgKxOiELPr0mXfEuFEjOLN8brUzi_oIildPSjHkhenc5fPpkcM&__tn__=*NK-R) #BuildInPublic (https://web.facebook.com/hashtag/buildinpublic?__cft__[0]=AZgkO2m3tWjeIYVQtrW1jYz-ciuphO-zGjm9gVKGk4f2vsTTraxReWYehX2nb-v-ZARrZN_8X0vP7GRxjUiW0_Oeqtn6Aq8kufxBbW58KIWnSXRQGNj6QsBJapY1qfM0PBS-hifRALgKxOiELPr0mXfEuFEjOLN8brUzi_oIildPSjHkhenc5fPpkcM&__tn__=*NK-R)
4
2
536
Cover image for Will you learn basics or use AI as the basics#BuildInPublic ...
Will you learn basics or use AI as the basics#BuildInPublic #LearnToCode ##AIENGINEER #founders
1
2
351