Search Results

Search Results

Query: agents
Found 33 results
  • AGENTS

    _private/qwestly-private-docs/SOC2/AGENTS.md
    # AGENTS.md โ€” SOC2 Compliance Documentation ## Context This directโ€ฆ
  • openai-harness-engineering-summary

    articles/openai-harness-engineering-summary.md
    โ€ฆts, CI, docs, observability, tooling โ€” was written by Codex agents, not humans. The practice of designing the environment agenโ€ฆ
  • linkedin-and-resume-grader-tech-design

    _private/qwestly-docs/Features/plan/linkedin-and-resume-grader-tech-design.md
    โ€ฆYSTEM_PROMPT`) Current flow description (lines 220-226 of `agents/prompts.py`): ``` 1. Introduce yourself briefly 2. Ask forโ€ฆ
  • unauthenticated-agent-onboarding-tech-design

    _private/qwestly-docs/Features/plan/unauthenticated-agent-onboarding-tech-design.md
    โ€ฆnly a ~20-line subclass โ€” no existing code is touched. ``` agents/ โ”œโ”€โ”€ prompts.py โ† ORCHESTRATOR_SYSTEM_PROMPTโ€ฆ
  • architecture-overview

    _private/qwestly-docs/Features/qwestly-agent/architecture-overview.md
    โ€ฆser request, figures out intent, and dispatches work to sub-agents or tool calls. No framework-specific opinions here โ€” just tโ€ฆ
  • bonus-topics

    _private/qwestly-docs/Features/qwestly-agent/bonus-topics.md
    โ€ฆroduction observability. --- ## 1. Prompt Engineering for Agents This is the single most important skill in building agentiโ€ฆ
  • deployment-options

    _private/qwestly-docs/Features/qwestly-agent/deployment-options.md
    โ€ฆs** | 10 | 100 (soft) | Custom | **The hard constraint for agents is function timeout.** An agent loop with 2-3 tool calls aโ€ฆ
  • framework-comparison

    _private/qwestly-docs/Features/qwestly-agent/framework-comparison.md
    โ€ฆe-playing, task delegation | Low | High | โญโญโญโญ | | **OpenAI Agents SDK** | Python | Single-agent tool-use, simplicity | Low |โ€ฆ
  • human-in-the-loop

    _private/qwestly-docs/Features/qwestly-agent/human-in-the-loop.md
    โ€ฆs `interrupt_before` pattern: ```python graph = StateGraph(AgentState) graph.add_node("call_llm", ...) graph.add_node("executโ€ฆ
  • index

    _private/qwestly-docs/Features/qwestly-agent/index.md
    โ€ฆtic frameworks in 2026 โ€” LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, Pydantic AI, Semantic Kernel, Dify, and more. Trade-ofโ€ฆ
  • profile-edit-tool

    _private/qwestly-docs/Features/qwestly-agent/profile-edit-tool.md
    โ€ฆt-side. ### 4.3 Orchestrator Prompt The system prompt in `agents/orchestrator.py` describes all tools and instructs the LLMโ€ฆ
  • qwestly-agent-orchestration-plan

    _private/qwestly-docs/Features/qwestly-agent/qwestly-agent-orchestration-plan.md
    โ€ฆtart with a single orchestrator + tools, add specialist sub-agents as the prompt grows too complex. --- ## System Architectuโ€ฆ
  • rag-and-tools-patterns

    _private/qwestly-docs/Features/qwestly-agent/rag-and-tools-patterns.md
    โ€ฆritical design decision. Mixing them up leads to unreliable agents. ### Use a TOOL when: - **The data is structured**. Userโ€ฆ
  • testing-agentic-systems

    _private/qwestly-docs/Features/qwestly-agent/testing-agentic-systems.md
    โ€ฆpython assert add(2, 2) == 4 # Always passes, forever ``` Agents are non-deterministic: ```python result = await agent.run(โ€ฆ
  • adam

    _private/qwestly-private-docs/HR/Personnel/adam/adam.md
    โ€ฆing prototype; now collaborating on bite-size interview sub-agents - **David** โ€” brought in as intern Jul 2025, converted to fโ€ฆ
  • dominick

    _private/qwestly-private-docs/HR/Personnel/dominick.md
    โ€ฆ06** using DeepSeek Flash - **Bite-size interview** โ€” 5 sub-agents for different value propositions - **Centralized prompt exeโ€ฆ
  • vela

    _private/qwestly-private-docs/HR/Personnel/vela/vela.md
    โ€ฆs for production prompts completed; bite-size interview sub-agents; document generation system | | Present | Qwestly agent intโ€ฆ
  • CLAUDE

    _private/qwestly-private-docs/SOC2/CLAUDE.md
    See [AGENTS.md](AGENTS.md).
  • deepseek

    AI/deepseek.md
    โ€ฆde Code tools (file read/edit/write, bash, glob, grep, git, agents, cron, skills, etc.) are provided by the **Claude Code harnโ€ฆ
  • oh-my-pi

    AI/oh-my-pi.md
    โ€ฆ` (user) | | Claude | 80 | `.claude/` directories | | Codex/Agents | 70 | `.codex/` directories | | Gemini | 60 | `.gemini/` dโ€ฆ
  • pi-coding-agent

    AI/pi-coding-agent.md
    โ€ฆty packages that follow the [Agent Skills standard](https://agentskills.io). They're simpler than MCP โ€” a skill is just a foldโ€ฆ
  • skills

    AI/skills.md
    โ€ฆview-toolkit/` - **Mechanism**: Launches specialized review agents (code-reviewer, silent-failure-hunter, comment-analyzer, prโ€ฆ
  • workspace-harness

    AI/workspace-harness.md
    โ€ฆlding within a connected set of repositories, leveraging AI agents with cross-repo context. ## Philosophy A workspace harnesโ€ฆ
  • founders-coding-again-summary

    articles/founders-coding-again-summary.md
    โ€ฆdically different outputs. A leader who can't read the code agents produce is flying blind. - **Judgment compounds.** When AIโ€ฆ
  • vercel

    documents/dev/vercel.md
    โ€ฆlows is a fully managed platform for durable functions / AI agents (JS, TS, Python). Mark a function as a workflow by placingโ€ฆ
  • bring-your-own-agent-acp-portable-editors

    posts/ideas/bring-your-own-agent-acp-portable-editors.md
    โ€ฆโ€” open standard from Zed/Anthropic/Cursor, like LSP for AI agents - **Avante.nvim** โ€” Neovim plugin that spawns any ACP agentโ€ฆ
  • engineering-harness-ai-bottleneck-approval

    posts/ideas/engineering-harness-ai-bottleneck-approval.md
    โ€ฆssuming humans would do most of the work. Then we built AI agents that could read and write our docs, search our meetings, maโ€ฆ
  • AI-powered-development

    presentations/AI-powered-development.md
    โ€ฆtly Engineering Learning Series ## AI-Powered Code Editing, Agents, and Custom Toolchains > Engineering Excellence > 2026 --โ€ฆ
  • agent-conversations-schema-redesign

    qwestly-workspace/docs/agent-conversations-schema-redesign.md
    โ€ฆ`is_system`) 3. **Update SSE streaming** in `qwestly-agent/agents/base.py`: - Read `part.tool_call_id` from Pydantic AI'sโ€ฆ
  • mac-studio

    services/mac-studio.md
    โ€ฆtop is via launchd: ```bash launchctl load ~/Library/LaunchAgents/com.user.ttyd.plist # start launchctl unload ~/Libraryโ€ฆ
  • openclaw

    services/openclaw.md
    โ€ฆnfig โ”œโ”€โ”€ workspace/ # Working directory โ”‚ โ”œโ”€โ”€ AGENTS.md # Agent behavior guide โ”‚ โ”œโ”€โ”€ SOUL.mdโ€ฆ
  • agent-drafts-linkedin-suggestion

    _private/qwestly-docs/Features/qwestly-agent/agent-drafts-linkedin-suggestion.md
    # Agent Drafts & LinkedIn Profile Suggestion ## Overview The qwestly-agent can generate LinkedIn About sections using the same LangSmith prompt as the candidate app's admin LinkedIn Suggestions page
  • Internship Agreement - Cohen Russell

    _private/qwestly-private-docs/HR/Personnel/cohen/Internship Agreement - Cohen Russell.md
    # QWESTLY INTERNSHIP AGREEMENT **This Agreement** is between Qwestly, Inc. ("Qwestly" or "the Company") and Cohen Russell ("Intern") and his parent/guardian ("Parent/Guardian"). ## **1. Internship T