Agent Orchestration | Techlist.io

githubApr 1, 20263 min readCurated summary

Run multiple agents at once with /fleet in Copilot CLI

GitHub Copilot CLI’s `/fleet` command lets multiple subagents work on independent tasks simultaneously rather than completing everything sequentially. An orchestrator decomposes the objective, manages dependencies, dispatches agents, and verifies their results. To benefit from parallel execution, users should define clear deliverables, boundaries, dependencies, and validation requirements. ## How `/fleet` Works - Breaks a task into discrete work items and identifies dependencies. - Runs independent items in parallel as background subagents. - Waits for completed work before dispatching dependent tasks. - Verifies results and assembles the final output. - Gives each subagent its own context window while sharing the same filesystem. - Prevents direct communication between subagents; the orchestrator coordinates them. ## Getting Started - Run `/fleet <objective prompt>` interactively, such as: ```bash /fleet Refactor the auth module, update tests, and fix the related docs in docs/auth/ ``` - For terminal-based non-interactive use: ```bash copilot -p "/fleet <YOUR TASK>" --no-ask-user ``` - The `--no-ask-user` option is required when no one is available to answer prompts. ## Writing Parallelizable Prompts - Define concrete deliverables such as individual files, test suites, or documentation sections. - Avoid vague requests that make it difficult to identify independent work. - Explicitly state: - File or module ownership - Constraints, such as avoiding dependency changes - Required tests, linting, or type checks - List dependencies so the orchestrator can serialize only the necessary work while parallelizing the rest. ## Using Custom Agents - Specialized agents can be defined in `.github/agents/`. - Agent definitions may specify: - Model - Tools - Role-specific instructions - Prompts can assign different agents to different tracks, such as using a technical writer for documentation and the default agent for code. - If no model is specified, the agent uses the current default model. ## Monitoring Fleet Execution - Review the initial decomposition to ensure the task has multiple independent tracks. - Use `/tasks` to inspect active background work. - Look for progress updates from separate tracks. - If work is proceeding sequentially, ask Copilot to decompose the task first and report each track’s status and blockers. ## Avoiding File Conflicts - Subagents share a filesystem without file locking. - If two agents edit the same file, the last completed write silently overwrites the other. - Assign distinct files or directories to each track. - For shared files, use temporary outputs and merge them afterward, or impose an explicit execution order. Use `/fleet` for well-partitioned work with clear ownership and dependencies. Careful prompt structure is essential: parallelism is most effective when agents can operate independently without competing for the same files.

Read original

Agent Orchestration Multi Agent Systems Github Copilot Cli Slash Commands+2

figmaMar 17, 20262 min readCurated summary

Design’s Influence Is Expanding, and Here’s Why That Feels Hard | Figma Blog

Design is expanding into more products, interactions, and strategic decisions, especially as AI introduces new software categories and interfaces. Although AI makes design work faster, it also increases output, expectations, and workload rather than reducing effort. This leaves designers divided: the field is growing, but many are unsure whether it is improving. ## Design’s Expanding Influence - Each technological shift—from graphical interfaces to the web and mobile apps—has increased design’s scope. - AI is creating new categories such as agent orchestration systems and answer engines. - Existing products are gaining generative, conversational, and predictive features. - Users now interact through prompts, speech, and image uploads, creating new design challenges: - Translating ambiguous input into clear intent - Making automated experiences understandable and human - Designing beyond traditional screen-by-screen navigation - Survey results show mixed sentiment: - 36% of designers think the profession has improved - 35% think it has worsened - 29% see no change - Meanwhile, 82% of hiring managers say demand for designers has increased or remained steady, though only 20% believe the industry itself is improving. ## AI Expands the Work - AI helps teams address new design problems more quickly, but it does not necessarily reduce the amount of work. - Product builders reported a 17.5% year-over-year increase in the number of tasks they perform. - Research from UC Berkeley found that AI users work faster while also taking on more tasks and working longer hours. - Workers often feel more productive without feeling less busy. ## The Jevons Paradox in Design - As AI makes creation cheaper and easier, teams produce more designs, explore more options, and iterate more deeply. - This follows the Jevons Paradox: efficiency increases can lead to greater overall consumption rather than reduced consumption. - Software development experienced a similar pattern when cloud infrastructure made releases easier, resulting in more frequent releases and redesigns. - AI has changed the rhythm and volume of design work rather than eliminating it. Designers should view AI as a force multiplier, not a shortcut to less work. Its benefits will depend on managing rising expectations and workload while developing clearer approaches to complex, automated interactions.

Read original

Agent Orchestration AI Generative AI User Experience Design+3

microsoftDec 3, 20253 min readCurated summary

The Interaction Changes Everything: Treating AI Agents as Collaborators, Not Automation

The article argues that effective AI agents should be treated as engineering collaborators, not automation scripts. Microsoft applied this approach to migrate hundreds of repositories from Entra SDK v1 to v2, reducing work from 4–6 weeks per repository to under two hours with 80–90% accuracy. The key improvement came from giving the agent a role, mission, priorities, and permission to exercise judgment. ## The Entra SDK Migration Challenge - The migration involved hundreds of repositories and sensitive authentication security boundaries. - Traditional migrations required extensive human review and took 4–6 weeks per repository. - The AI agent completed comparable work in under two hours while achieving 80–90% accuracy. - The goal was not merely speed, but reliable handling of custom configurations, edge cases, and security concerns. ## Problems with Automation Thinking - Initial attempts treated the agent like a script executor: - Detailed transformation instructions were provided. - Every anticipated edge case was documented. - The agent was expected to follow a checklist. - This approach repeatedly failed because complex migrations require: - Context-dependent decisions - Handling of undocumented patterns - Security-boundary evaluation - Trade-offs between correctness, speed, and preservation of custom logic - The central lesson is that judgment cannot be fully automated, but it can be supported through collaboration with an intelligent agent. ## Identity Instead of Instructions - The team reframed the agent as a member of the migration team rather than a tool. - The prompt described the agent as a “co-creative engineer” expected to: - Use judgment - Stay curious - Act carefully - Ask for help when uncertain - This change improved accuracy and edge-case handling. - The agent was more likely to surface uncertainty instead of guessing or failing silently. ## The Co-Creative Partnership Framework ### Identity and Mission - Establish the agent’s team, mission, and the importance of the work. - Explicitly state that the agent is not a script executor. - Explain why the task matters so the agent can prioritize appropriately. - Encourage judgment, curiosity, and care. ### Purpose and Intent - Describe the guide as supporting both human and AI team members. - Make priorities explicit, such as security over speed or correctness over completion. - Allow autonomy when repository contexts differ. - Frame uncertainty as a reason to collaborate rather than as failure. ### Prioritized Goals - List primary, secondary, quality, and human-in-the-loop objectives in order. - Explicit priorities help the agent resolve conflicts. - Including quality and collaboration prevents optimizing for speed alone. ### Step-by-Step Guidance with Judgment - Provide concrete actions, conditional logic, edge-case handling, and before-and-after examples. - Specify what must remain unchanged, including custom logic. - Define situations requiring escalation, such as unusual patterns, ambiguity, or possible security violations. - The framework combines procedural guidance with room for context-sensitive decisions. ## Practical Recommendation For complex migrations, security reviews, or architectural work, write prompts that define a collaborative role and decision-making framework—not just a list of commands. Give the agent context, priorities, preservation rules, examples, and clear escalation points so it can act autonomously while knowing when human judgment is required.

Read original

Agent Orchestration AI Agents Github Copilot Prompt Engineering+3

googleOct 26, 2025Original article

How we are building the personal health coach (opens in new tab)

Google is leveraging Gemini models to create a proactive, adaptive personal health coach designed to bridge the gap between fragmented health data and actionable wellness guidance. By integrating physiological metrics with behavioral science, the system provides tailored insights and sustainable habit-building plans through a sophisticated multi-agent AI architecture. This initiative, currently in public preview for Fitbit Premium users, represents a transition toward data-driven, expert-validated health coaching that evolves dynamically with an individual's progress. ## Architecting a Multi-Agent Health Coach The system utilizes a complex multi-agent framework to coordinate different specialized AI sub-agents, ensuring that health recommendations are holistic and contextually aware. * **Conversational Agent:** Manages multi-turn interactions, understands user intent, and orchestrates the other agents while gathering necessary context for response generation. * **Data Science Agent:** Employs code-generation capabilities to iteratively fetch, analyze, and summarize physiological time-series data, such as sleep patterns and workout intensity. * **Domain Expert Agent:** Analyzes user data through the lens of specific fields like fitness or nutrition to generate and adapt personalized plans based on changing user context. * **Numerical Reasoning:** The coach performs sophisticated reasoning on health metrics, comparing current data against personal baselines and population-level statistics using capabilities derived from PH-LLM research. ## Ensuring Reliability via the SHARP Framework To move beyond general-purpose AI capabilities, the system is grounded in established coaching frameworks and subjected to rigorous technical and clinical validation. * **SHARP Evaluation:** The model is continuously assessed across five dimensions: Safety, Helpfulness, Accuracy, Relevance, and Personalization. * **Human-in-the-Loop Validation:** The development process involved over 1 million human annotations and 100,000 hours of evaluation by specialists in fields such as cardiology, endocrinology, and behavioral science. * **Expert Oversight:** Google convened a Consumer Health Advisory Panel and collaborated with professional fitness coaches to ensure the AI's recommendations align with real-world professional standards. * **Scientific Grounding:** The coach utilizes novel methods to foster consensus in nuanced health areas, ensuring that wellness recommendations remain scientifically accurate through the use of scaled "autoraters." Eligible Fitbit Premium users on Android in the US can now opt into the public preview to provide feedback on these personalized insights. As the tool evolves through iterative design and user research, it aims to provide a seamless connection between raw health metrics and sustainable lifestyle changes.

Agent Orchestration Code Generation Multi Agent Systems Ai Evaluation+4