Skip to content
Mitul Shah

Case Study — Featured Work

AI-Powered Partner Management Framework

An MCP-based AI framework that automates the operational overhead of managing strategic partner relationships — built solo, then scaled to a whole Solutions Architect team.

  • 5–8hrs

    saved per SA, per week

  • 6+tools

    unified behind one interface

  • 30sec

    meeting prep — down from 15+ minutes

  • $0

    infrastructure cost — runs entirely in the IDE

The problem

Partner-facing Solutions Architects lose hours every week to operational overhead: prepping for meetings across email, Slack, and tickets, writing notes, tracking action items, compiling executive updates, and context-switching across 6+ tools.

What it is

An AI-powered framework built in Kiro IDE, connected via Model Context Protocol (MCP) integrations to email, Slack, ticketing, documentation, and platform-docs systems — with persistent partner context through steering files and automated workflows through agent hooks.

Capabilities

  • Meeting prep in ~30 seconds

    Auto-pulls emails, Slack threads, tickets, and meeting history — what used to take 15+ minutes of tab-hopping.

  • Automated meeting notes

    Paste raw notes → formatted files with action items extracted and TODO lists updated.

  • Partner health checks

    Scored dashboards across five categories — Technical, Delivery, Communication, Action Items, Risk — with staleness detection and trend tracking.

  • Executive summaries

    Polished HTML dashboards ready to send to leadership, generated on demand.

  • COE document builder

    Correction-of-error documents with interactive 5 Whys analysis and self-review.

  • Partner handoffs

    Handoff documents that adapt for temporary coverage vs. permanent transfer.

  • Ticket tracking

    Paste a ticket URL → auto-tracked with status updates; bulk one-click refresh with stale-ticket flagging.

  • Proactive date alerts

    Upcoming deadlines and overdue items surfaced across all partners.

  • Papercuts mechanism

    SAs log operational friction to a shared doc from any conversation in under 60 seconds — giving managers visibility into systemic issues.

  • Self-learning loop

    End-of-conversation hooks prompt saving new knowledge back to the knowledge base; in-conversation awareness catches gaps in real time.

  • Privacy controls

    Per-partner choice of shared or local-only data with a single agent command.

  • Platform troubleshooting

    The agent reads platform docs via MCP to diagnose partner app issues and draft technical responses with code examples.

Adoption & community

Built solo — then turned into a team platform.

  • Delivered a 1-hour presentation + hands-on workshop at SA Summit to ~20 Solutions Architects, with two interactive exercises — a ticket-intake workflow and live technical bug troubleshooting.
  • Contribution guide with an agent-assisted code-review workflow designed for non-developers — the agent walks contributors through CLI setup, git staging, and the review process.
  • Kanban board with 20+ tracked tasks across backlog → released; structured release mechanism with a mainline/staging branching model.
  • 12 weeks of Monday "power-user tips" covering context management, workflow patterns, and agent optimization.
  • Wiki, README, workshop guide, and self-paced exercises for ongoing onboarding; weekly office hours.
  • Teammates actively contributing hooks — an email digest, a gamified stats tracker — through a maintained review process.

Outcomes

  • Institutional knowledge compounds — every interaction feeds the partner knowledge base.

  • Staleness detection catches dropped items before they become problems.

  • In production use across multiple strategic partner relationships.

Want the full story?