AI Workflows & Agentic Architecture Directory

Inspired by SUPERAGENT 3.0 (August 11, 2026), the AI business partner for insurance agencies, this dispatch builds agency-ops-mcp, a FastMCP TypeScript server exposing read-only quote data, policy and CRM lookup, and compliance status to agents. Write tools for quote generation and policy updates are gated behind OAuth scopes plus a human approval gate, and every action is written to an append-only audit trail.

Alteryx Agent Studio (Inspire 2026) lets business analysts convert trusted data workflows into autonomous agents without IT. This dispatch builds analyst-deploy, a LangGraph workflow with a three-stage pipeline: an analyst defines rules in a structured spec, an agent builder compiles the spec into a deployable agent with tool mappings, and a governance gate enforces approvals, a scope allowlist, and audit before pushing to Slack, Teams, or an external model channel. Rollback and versioning are first-class.

The 2026 agent-browser wave (Cloudflare Kitesurf) and QF-Test 11.0.1's MCP server let Claude Code and GitHub Copilot plug into automated testing. This dispatch builds web-native-tester, a LangGraph workflow that drives a lightweight headless browser runtime, orchestrates web-platform tests via an MCP server, collects results, and routes failures into a human-fix loop with retry and regression tracking.

Code for India's Code for a Billion — Bharat Agentic-AI Hackathon 2026 (Aug 15, 2026) targets education, health, climate, governance, and financial inclusion. This dispatch builds civic-serve, a LangGraph workflow that turns public-service intents into governed agent actions: intake plus eligibility check, privacy-gated data access, multilingual output, human approval for entitlement-changing actions, and an append-only audit for public-sector transparency compliance.

Microsoft's June 30, 2026 security guidance formalizes the shift from read-only assistants to read-write operators: agents that draft email, create docs, and update calendars through MCP. The impact profile moves from biasing an output to triggering an action. This briefing covers read-write boundary design, least-privilege scopes, and approval gates enforced outside the model.

In 2026, tool names and descriptions became the agent's instruction context: a poisoned description is a system prompt written by the attacker. MCP tool poisoning abuses the protocol's discovery model, where every connected server contributes tokens to the agent's brain. Verification, description allowlists, and treating metadata as untrusted are the working defenses.

Two July 2026 incidents — claude.ai's Memory Heist and Noma Security's GitLost — proved agents with fetch and send capabilities are exfiltration devices. Both attacks share one spine: indirect prompt injection converted into data theft. Egress allowlists and fetch sandboxing are now the baseline controls for agentic systems.

DeepSeek's August 2026 release open-sourced the agent harness — tools, memory, orchestration, and eval loop — completing the commoditization of the agent stack. With Agent = Model + Harness and both halves open, differentiation moves to evals, data, and integrations. The make-vs-buy math has changed.

On August 14, 2026, Kredily 3.0 launched KAI, agentic AI for payroll and HR serving 25,000+ businesses and 1M+ employees. Payroll is the least forgiving software category in business, and KAI shows the winning pattern: a deterministic engine, agents for mechanical work, and hard approval gates for money movement.

In August 2026, an AI research agent called Primus generated 30 papers in a month, and Google DeepMind cited one of them. The integrity crisis is structural: no provenance standard, weak forensics, and no accountability for agent outputs. The fix is provenance, not detection alone.

Inspired by Kredily 3.0's KAI launch on August 14, 2026, this dispatch builds payroll-hr-mcp, a FastMCP TypeScript server exposing read-only payroll overview, attendance, statutory compliance, and pay-slip queries to agents. Write tools — payslip runs and reimbursement approvals — are gated behind a human-approval workflow with OAuth 2.0 enforcement.

Inspired by Microsoft's June 30, 2026 read-write agent shift, this dispatch builds rw-boundary-mcp, a FastMCP TypeScript server wrapping office/document APIs. Read tools are always available; write tools require a scope token plus an approval gate, and every mutation is logged to an append-only audit trail.