Pillar
Multi-step chains, tool use, orchestration, feedback loops
29 articles • Page 2 of 4
BUILD 2026 made code-as-action a first-class pattern. Here's how to rewrite your tool-use prompts from "pick a tool" to "write code that calls the tools" and cut tokens 30-50%.
Microsoft's new Handoff orchestration pattern proves the routing decision isn't architecture, it's a prompt. Here's how to write it so your agents don't deadlock or drop context.
The IdleSpec technique turns dead wait time into planning cycles that cut agent task completion by 40%
The prompting discipline for persistent background agents is fundamentally different from chat -- here's the pattern that keeps autonomous actions safe and useful.
Anthropic shipped the grading loop -- the rubric is now the hardest prompt you'll write
ADK 1.0 and the A2A protocol turned your agent's metadata into the most important prompt you're not optimizing
Anthropic's Managed Agents, Google ADK, and Microsoft Agent Framework 1.0 all abstract away the runtime -- your prompts need to catch up
Stop burning your million-token window on grep output. Prompt patterns that decide what gets delegated.
The structured handoff format that makes multi-agent pipelines actually reliable
