thataidevΒ·2d agoWhen AI Agents Call the Wrong Tool: The Hidden Problem With Tool SelectionOne of the most impressive things about an AI agent is its ability to use tools.
thataidevΒ·Nov 5Context Rot: When More Context Makes AI WorseWe spent a lot of time teaching AI models to handle longer conversations.
thataidevΒ·Nov 2AI Agents Need Guardrails, Not Just IntelligenceAn AI agent can plan a task, call tools, retrieve information, and take action with surprisingly little human intervention.
thataidevΒ·Oct 31AI Observability: What Happens After Your AI Goes Live?Getting an AI application to work in a demo feels great.
thataidevΒ·Oct 29AI Evaluation: Why Your AI Can Get Worse Without Anyone NoticingThereβs something tricky about shipping an AI feature.
thataidevΒ·Oct 27AI Hallucinations: When an LLM Sounds Confident but Gets It WrongOne of the strangest things about working with AI is that it can give you a completely wrong answer with complete confidence.
thataidevΒ·Oct 24What Is Backpressure in AI Systems? When Requests Arrive Faster Than They Can Be ProcessedImagine your AI application is working perfectly.
thataidevΒ·Oct 21What Is an AI Memory System? How AI Agents Remember Past InteractionsEver had to explain the same thing to an AI assistant every time you opened a new conversation?
thataidevΒ·Oct 19Why AI Agents Fail in Production: Retries, Timeouts, and RecoveryAn AI agent works perfectly in a demo.