IBM Bob

image

IBM Bob

Bob is your AI development partner, built to augment your workflow and help you work confidently with codebases from design to deployment.


#AI

#IBMBob

 View Only

IBM Bob – Build & Review Touchpoint (Part 2)

By Narendra Murthy posted Fri April 10, 2026 10:30 AM

  

IBM BOB

Build & Review

Context · Modes · Code Review · MCP

Master context mentions, build reusable custom modes, and connect Bob to external tools

Labs 3–5     All Labs    Resources

Continuation from March 26th Touchpoint

By the end of exercise you will: use all context mentions types fluently, write multi-step literate coding instructions, run AI-powered code reviews with /review, build a custom Security Reviewer mode in YAML, and configure an MCP server.

    Lab 3: Context mentions, literate coding deep-dive, /init and AGENTS.md

    Lab 4/5: Code reviews, custom modes (YAML), MCP server configuration

Time commitment: 3–4 hours per week

Prerequisites: Lab 1 & 2 complete. Bob IDE running, IBM/bob-demo cloned.

FN 1

Get Started

FN 2 ← NOW

Build & Review

FN 3

Modernize

FN 4

Ship & Scale

Fortnight 2 — Learning Plan

  Context Mastery, Literate Coding & AGENTS.md

Context Mastery, Literate Coding & AGENTS.md

Objective: Master all 7 @ mention types, write multi-step literate coding instructions, and give Bob persistent project context with /init.

📖 Required Reading

    Context mentions — all 7 types, ignore-file interactions, combining mentions

    Literate coding — Cmd/Ctrl+M, generate, accept, reject, multi-block usage

    Start a project with /init and AGENTS.md

    Context window management

    Context poisoning — what it is, how to avoid it

🎬 Videos (youtube.com/@ibm-bob)

    Literate Coding in Action — generate code from plain-English comments

    Bob Shell in Your Terminal

🔬 Lab 3

     Context Mastery — use all 7 mention types, multi-step literate coding, /init and AGENTS.md

📝 Power Prompts to Try

# File comparison (2 @ mentions in one prompt):

@/src/db.ts @/src/index.ts  How do these relate? What data flows between them?

# Fix all diagnostics at once:

@problems  Fix all these issues and explain what was wrong.

# Debug from terminal output:

@terminal  What went wrong and how do I fix it?

# Commit message from staged changes:

Suggest a conventional commit message for @git-changes

# Live documentation reference:

@https://bob.ibm.com/docs/ide/features/literate-coding  Summarise this page.

✅ Lab 3 Checklist

    Used @/src/... to reference a specific file

    Used @problems to fix all diagnostics in one go

    Used @terminal to debug a failing command

    Used @git-changes to generate a commit message

    Used @URL to fetch live documentation

    Wrote a multi-step literate coding instruction across 3 file locations

    Ran /init and reviewed the generated AGENTS.md

  Code Reviews, Custom Modes & MCP

Code Reviews, Custom Modes & MCP

Objective: Run AI-powered code reviews, build a reusable custom mode for your team, and configure Bob with an MCP server.

📖 Required Reading

    Code reviews — Review Panel, /review, Bob Findings, issue coverage mode

    Custom modes — YAML format, tool groups, file restrictions, overriding defaults

    Understanding MCP

    MCP server transports — stdio vs streamable-http

    Security guidelines — credentials, .bobignore, MCP security

🎬 Videos (youtube.com/@ibm-bob)

    Shift-Left Code Review — security and quality before CI/CD

    IBM Bob Modes Demo

🔬 Labs

    Lab 4: Code Review — /review, Bob Findings panel, ZAP scan prompt, configure exclusions

    Lab 5: Custom Mode + MCP — Security Reviewer mode in YAML, .bob/mcp.json, MCP tools in Advanced mode

📋 Performance Insights Mode — Real Config from IBM Bob Team

This is the exact Performance Insights mode configuration used in IBM Bob team demos:

Name: Performance Insights

Slug: performance-insights

API Configuration: Premium

Role Definition:

  You are an experienced performance analyst. Your goal is to gather

  information, analyse performance data, and provide insights on the

  data that developers, architects and project managers can understand.

Short description: Get insights on performance data

Available Tools: Read Files, Edit Files, Use Browser, Run Commands, Use MCP

Custom Instructions:

  Make key summary statements supported with tabular data. Identify trends,

  patterns, anomalies and performance issues. Focus on customer impact.

  Assume an SLA of P95 < 10 seconds for the analysis.

✅ Lab 4 Checklist

    /review ran on uncommitted changes, Bob Findings panel populated

    At least 3 findings triaged (Fix, Resolve, Dismiss)

    Custom Security Reviewer mode created in .bob/custom_modes.yaml

    Mode-specific rule file in .bob/rules-security-reviewer/

    .bob/mcp.json configured with at least one MCP server

    .bob/mcp.json verified in .gitignore — no hardcoded credentials

Fortnight 2 — Labs

All labs use github.com/IBM/bob-demo. Make sure you have it cloned from Fortnight 1.

Lab 3 — Context Mastery & AGENTS.md

Overview

Time: ~50 min   |   Difficulty: Intermediate   |   Modes: Ask, Code

Goal: Use all 7 @ mention types fluently and set up AGENTS.md for persistent project context.

Context Exercises

1.    File comparison.

@/src/db.ts @/src/index.ts  How do these relate? What data flows between them?

2.    @problems fix-all. Introduce a deliberate TypeScript error, then:

@problems  Fix all these issues and explain what was wrong with each one.

3.    @terminal debug. Run a failing build, then:

@terminal  What went wrong and how do I fix it?

4.    @git-changes commit. Stage changes, then:

Suggest a conventional commit message for @git-changes

5.    @URL fetch.

@https://bob.ibm.com/docs/ide/features/literate-coding  Summarise how literate coding works.

6.    Multi-step literate coding. Open a source file. Toggle Cmd/Ctrl+M. Write 3 instruction comments in 3 different locations. Click Generate. Observe how Bob resolves all 3 as one coherent change.

/init and AGENTS.md

7.    Run /init. In the bob-demo project root, type /init in chat. Bob generates AGENTS.md.

8.    Inspect AGENTS.md.

@AGENTS.md  What persistent instructions did /init add? How will they affect Bob?

9.    Test persistence. Start a new chat. Ask a coding question. Note that AGENTS.md rules apply even in a fresh conversation.

✅ Success Criteria

    All 7 mention types used at least once in this lab session

    Multi-step literate coding change generated and accepted

    AGENTS.md created by /init and rules visible in fresh conversations

Lab 4 — Code Review: /review & Bob Findings

Overview

Time: ~45 min   |   Difficulty: Intermediate   |   Modes: Code, Review

Goal: Run AI-powered code reviews, triage Bob Findings, and use the OWASP ZAP scan prompt.

Steps

10. Add a vulnerable route. In Code mode, ask Bob to add a new API route with no input validation.

11. Run /review.

/review main

12. Triage findings. "Fix with Bob" for security issues, "Mark as Resolved" for intentional patterns, "Dismiss" for non-applicable items.

13. OWASP ZAP scan prompt (Bob Shell). If you have OWASP ZAP 2.16.1+, scan localhost:3000. Then:

bob -p "Explain and resolve the OWASP ZAP Scan results from @report.html"

14. Configure exclusions. Settings → Bob Findings → Review Exclusions. Add: *.test.ts and .vscode/**

15. Re-run /review. Confirm excluded files no longer appear in findings.

✅ Success Criteria

    At least 3 findings visible in Bob Findings panel after /review

    One finding fixed with Bob, one marked resolved, one dismissed

    Exclusions working — excluded files absent from next run

Lab 5 — Custom Mode + MCP Integration

Overview

Time: ~60 min   |   Difficulty: Intermediate   |   Modes: Custom mode, Advanced

Goal: Build a Security Reviewer mode in YAML and configure an MCP server from IBM/bob-demo/bob-modes.

Part A — Security Reviewer Custom Mode

16. Settings → Modes → +. Create:

Name: 🔒 Security Reviewer   |   Slug: security-reviewer

Role: You are a security-focused code reviewer. You identify OWASP Top 10

      vulnerabilities, credential leaks, and injection risks. Report each

      finding with severity (High/Medium/Low) and a specific code fix.

Tools: read only (no edit, no command, no mcp)

17. Add rule. Create .bob/rules-security-reviewer/01-output.md:

## Output Format

### [HIGH/MED/LOW] Finding Title

**File:** path/to/file.ts:line   **Issue:** description   **Fix:** code change

18. Test. Switch to Security Reviewer. Ask:

@/src  Review this directory for OWASP Top 10 vulnerabilities.

Part B — MCP Configuration

19. Read the bob-modes README.

@/bob-modes/README.md  Walk me through the setup steps for this demo.

20. Create .bob/mcp.json.

{

  "mcpServers": {

    "docs-langchain": {"type": "streamable-http", "url": "https://docs.langchain.com/mcp"},

    "next-devtools": {"command": "npx", "args": ["-y", "next-devtools-mcp@latest"]}

  }

}

21. Test in Advanced mode. "What MCP tools are available? List them with descriptions."

22. Security check. Verify .bob/mcp.json is in .gitignore with no hardcoded credentials.

✅ Success Criteria

    Security Reviewer mode in mode picker, outputs findings in correct format

    MCP tools listed and at least one invoked in Advanced mode

    .bob/mcp.json in .gitignore — zero hardcoded secrets

Key Resources

Docs: bob.ibm.com/docs   |   Download: bob.ibm.com/download

Demos: github.com/IBM/bob-demo   |   Tutorials: github.com/IBM/galaxium-travels

Videos: youtube.com/@ibm-bob   |   Product: ibm.com/products/bob

IBM Bob Customer Success Team

0 comments
23 views

Permalink