Create presentations using Amazon Bedrock AgentCore.
AWS shows an AI agent on Amazon Bedrock AgentCore that uses retrieval-augmented generation to create grounded slides and summaries from documents.
AI Agents in Practice
AI agents promise to do multi-step work on their own. This topic looks at what actually works today: real automations, no-code agent builders, coding agents and the guardrails you need before letting an agent touch your email, files or spreadsheets.
WideSWE: Can Coding Agents Synchronize Modifications Across Multiple Repositories?
WideSWE evaluates coding agents on 120 real multi-repo tasks, showing low full success and failures in discovery, execution, and completeness.
Quiz on Developing LLM Applications with Python
A diagnostic quiz for Python LLM apps, checking APIs, prompts, LangChain, RAG, embeddings, vector databases, agents, and MCP tool connections.
[Day 27/100] Workflows with Human Oversight: Approvals, Edits, and Interruptions
A reliable AI agent handoff pauses, transfers control to a human, and resumes from saved state, avoiding restarts and preserving approval context.
Announcing GPT-6.1 Sol
GPT-6.1 Sol claims near-Astra coding, agent, and professional work performance at 1/5 Astra API token prices; benchmarks remain unverified.
[Day 26/100] Cycles, Repetition, and Recognizing When to Stop
LangGraph cycles enable iterative agent workflows but can raise token, state, and observability costs, requiring clear stop conditions.
Citing Matthew Green
Sandboxed AI agents can still propagate harmful instructions via shared channels like email, Slack, docs, or Muse, creating a worm-like risk.
How to Build an AI Agent from Scratch in Python and Why It’s Worth It
This guide explains building a minimal AI agent in Python: define a goal, store messages, call a model, interpret actions, and stop safely.
Streamlining Financial Processes Using ChatGPT Work
Discover how finance professionals can use ChatGPT as a drafting partner and analytical assistant across four key workflows: monthly reporting commentary, variance analysis, forecasting support, and m…
How to Continue Using the Generative Pre-Trained Transformer 5.5 Model After the Chat Generative Pre-Trained Transformer Service Retired It
GPT-5.5 is retired from ChatGPT but remains available through the API, preserving access while changing memory, projects, and daily workflows.