Day 1/60 of #60DaysOfAgents 🔎 Fraud Desk is live: a multi-agent fraud and AML desk, built in public.
Shipped: a loader giving each transaction a tx_id agents must cite, and evals before any agent.
🔗 aurimas13/Fraud-Desk
#FraudDesk #AIAgents
🤝 Claude Code-assisted, reviewed by me.
3 likes · 79 views
Tomorrow I start Fraud Desk: 60 days building a multi-agent fraud and AML investigation desk in public. Evals before agents. A person approves every case.
🔗 aurimas13/Fraud-Desk
#60DaysOfAgents #FraudDesk #AIAgents
🤝 Claude Code-assisted, reviewed by me. t.co
1 like · 20 views
Day 100/100 of #100DaysWithAI 🏁
Day 1 was a decade of agents. Day 100 goes back to the prompt: be clear, let it think out loud, give it an out.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #PromptEngineering
🤝 Claude Code-assisted, reviewed by me.
1 like
Day 98/100 of #100DaysWithAI 🌿
Anthropic went from 2,500 to 30,000 merges a day and outgrew git. Its answer, Scion: always-online clients, commits on the server.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #DevOps
🤝 Claude Code-assisted, reviewed by me.
1 like
Day 97/100 of #100DaysWithAI 🖥️
Claude Code without a terminal: the desktop Code tab runs a session locally, in the cloud or over SSH, and shows each change as a diff.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me.
1 like
Day 97/100 of #100DaysWithAI 🖥️
Claude Code without a terminal: the desktop Code tab runs a session locally, in the cloud or over SSH, and shows each change as a diff.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me. t.co
1 like · 35 views
Day 96/100 of #100DaysWithAI 🧰
Yesterday: agent = model + harness. Today, Anthropic's quickstart that hosts the harness: agent, environment, session, events.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me.
1 like
Day 96/100 of #100DaysWithAI 🧰
Yesterday: agent = model + harness. Today, Anthropic's quickstart that hosts the harness: agent, environment, session, events.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me. t.co
2 likes · 28 views
Day 95/100 of #100DaysWithAI 🐎
11 coding-agent harnesses, ~4M lines of source: none imports an agent framework, none retrieves code with embeddings. They grep.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me.
2 likes
Day 95/100 of #100DaysWithAI 🐎
11 coding-agent harnesses, ~4M lines of source: none imports an agent framework, none retrieves code with embeddings. They grep.
🔗 aurimas13/100-Days-With-AI
#LearningInPublic #AgenticAI
🤝 Claude Code-assisted, reviewed by me. t.co
1 like · 30 views
Mentions
Day 1/60 of #60DaysOfAgents 🔎 Fraud Desk is live: a multi-agent fraud and AML desk, built in public. Shipped: a loader giving each transaction a tx_id agents must cite, and evals before any agent. 🔗 aurimas13/Fraud-Desk #FraudDesk #AIAgents 🤝 Claude Code-assisted, reviewed by me.
Tomorrow I start Fraud Desk: 60 days building a multi-agent fraud and AML investigation desk in public. Evals before agents. A person approves every case. 🔗 aurimas13/Fraud-Desk #60DaysOfAgents #FraudDesk #AIAgents 🤝 Claude Code-assisted, reviewed by me. t.co
Day 100/100 of #100DaysWithAI 🏁 Day 1 was a decade of agents. Day 100 goes back to the prompt: be clear, let it think out loud, give it an out. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #PromptEngineering 🤝 Claude Code-assisted, reviewed by me.
Day 98/100 of #100DaysWithAI 🌿 Anthropic went from 2,500 to 30,000 merges a day and outgrew git. Its answer, Scion: always-online clients, commits on the server. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #DevOps 🤝 Claude Code-assisted, reviewed by me.
Day 97/100 of #100DaysWithAI 🖥️ Claude Code without a terminal: the desktop Code tab runs a session locally, in the cloud or over SSH, and shows each change as a diff. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me.
Day 97/100 of #100DaysWithAI 🖥️ Claude Code without a terminal: the desktop Code tab runs a session locally, in the cloud or over SSH, and shows each change as a diff. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me. t.co
Day 96/100 of #100DaysWithAI 🧰 Yesterday: agent = model + harness. Today, Anthropic's quickstart that hosts the harness: agent, environment, session, events. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me.
Day 96/100 of #100DaysWithAI 🧰 Yesterday: agent = model + harness. Today, Anthropic's quickstart that hosts the harness: agent, environment, session, events. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me. t.co
Day 95/100 of #100DaysWithAI 🐎 11 coding-agent harnesses, ~4M lines of source: none imports an agent framework, none retrieves code with embeddings. They grep. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me.
Day 95/100 of #100DaysWithAI 🐎 11 coding-agent harnesses, ~4M lines of source: none imports an agent framework, none retrieves code with embeddings. They grep. 🔗 aurimas13/100-Days-With-AI #LearningInPublic #AgenticAI 🤝 Claude Code-assisted, reviewed by me. t.co