Tutorial 2: Develop Mode — AI on Existing Repositories

What you’ll accomplish: Connect a live Git repository, get an AI-generated codebase overview, ask natural-language questions about the code, and execute tasks — refactoring, bug fixes, new features, or test generation — autonomously.

Time to complete: 10–15 minutes for setup; tasks run in the background.

Prerequisites: An Ileen account with a credit balance and a Git repository URL (GitHub, GitLab, Bitbucket, or any Git host).

---

Overview

Develop Mode is built for teams with existing codebases. Instead of starting from scratch, you connect your repo and let Ileen’s AI understand your code before taking action.

Agent	What it does
🔌 Project Setup	Clones and indexes your repository
🔍 Project Overview	AI-generated analysis of your codebase
✍️ Prompt Engineer	Refines your task requests into precise AI prompts
📋 Task Queue	Executes development tasks on your codebase
💬 Code Query	Answers natural-language questions about your code

Use the interactive demo to explore each agent before connecting your own repo.

Interactive Demo💻 Develop

Step 1 / 5

🔌Project Setup●

›

🔍Project Overview🔒

›

✍️Prompt Engineer🔒

›

📋Task Queue🔒

›

💬Code Query🔒

🔌 Connect Repository

Repository URL

https://github.com/acme/legacy-crm

Base branch

main

Personal Access Token (private repos)

ghp_●●●●●●●●●●●●●●●●●●●●

Connect & Analyse →

What happens next: Ileen clones your repo, analyses the structure, and indexes all files so you can ask questions and run tasks immediately.

💡 Connect any Git repository using HTTPS or SSH. Provide a Personal Access Token for private repos. Ileen supports GitHub, GitLab, Bitbucket and any standard Git host.

← Back

Next →

---

Step 1 — Switch to Develop Mode

1. Open the Ileen app and look at the mode selector in the sidebar footer.
2. Click Develop to switch mode. The sidebar updates to show the Develop Mode agent pipeline.

---

Step 2 — Connect your repository

1. Click Project Setup in the agent pipeline.
2. Fill in the connection form:
   • Repository URL — HTTPS or SSH (e.g. https://github.com/acme/legacy-crm)
   • Base branch — the branch Ileen will analyse and work on (defaults to main)
   • Personal Access Token — required for private repositories; needs at least repo (GitHub) or read_repository + write_repository (GitLab) scopes
3. Click Connect & Analyse. Ileen clones the repository, analyses the structure, and indexes all files. This takes 1–5 minutes depending on repo size.

Note

Ileen works on a clone of your repository. Changes are committed and pushed back to your specified branch. Consider using a feature branch if you want to review changes before they reach main.

---

Step 3 — Read the Project Overview

Once indexing completes, the Project Overview agent generates a structured analysis of your codebase:

• Tech stack — languages, frameworks, key libraries, their versions
• Architecture summary — monolith vs. microservices, API style, frontend approach
• Key modules — most important files and directories
• Dependencies — outdated packages, known CVEs
• Potential risks — missing test coverage, deprecated patterns, N+1 queries, security concerns

Take a few minutes to read through this — it’s the fastest way to get oriented in an unfamiliar codebase, or to get a fresh perspective on one you know well.

---

Step 4 — Ask questions with Code Query

The Code Query agent lets you ask natural-language questions about your codebase and get precise, code-referenced answers.

Example questions you can ask:

• “How is authentication implemented? Is there 2FA?”
• “Which endpoints are not protected by authentication?”
• “Explain the database models and their relationships”
• “Where is Stripe integrated and how are webhooks handled?”
• “What does the nightly batch job do?”

The agent returns answers with:

• Code snippets with file path and line references
• Explanations of patterns and design decisions
• Warnings if something looks incorrect or insecure

You can keep the conversation going — follow-up questions maintain context from previous answers.

Session history

Every Code Query conversation is saved as a session. The Code Query view is split into two panes:

• Left — Session list: all past sessions with title, message count, and last-activity timestamp. Click any session to open it.
• Right — Session detail: shows the Last Answer (open by default, with a Copy button) and a collapsible Full conversation with every message in order.

Per-session actions:

• Resume (chat bubble icon) — reopens the session in the active chat, preserving all history so you can continue asking follow-ups.
• Delete (trash icon) — removes the session permanently.

Tip

Code Query is also useful during code review — ask it to explain a diff or summarise what a PR changes before you approve it. Resume old sessions to revisit the reasoning behind earlier decisions.

---

Step 5 — Create tasks with the Prompt Engineer

The Prompt Engineer bridges your plain-language request and the precise instruction the coding agent needs.

1. Click Prompt Engineer in the agent pipeline.
2. Type what you want to accomplish in natural language:
   • “Add test coverage to the billing module”
   • “Refactor the order listing endpoint to fix the N+1 query”
   • “Upgrade django-allauth to the latest version and fix any breaking changes”
3. The Prompt Engineer produces an optimised prompt that includes:
   • Specific files and functions to target
   • Expected output format
   • Edge cases and constraints
   • Testing instructions
4. Review the optimised prompt. You can edit it before sending.
5. Click Add to Task Queue to queue the task for execution.

---

Step 6 — Plan complex tasks with Task Plans

For tasks that require multi-file changes or careful coordination across repositories, use Task Plans instead of (or alongside) the Task Queue.

1. In the sidebar, click + New next to “Task Plans”.
2. Describe the task in plain language.
3. The AI evaluates your request against the full codebase and generates a detailed implementation plan — wait for the status to change from Evaluating to Planned.
4. Read the plan, then use the Discussion panel to ask questions or request adjustments.
5. When satisfied, click Approve → Execute.

Task Plans give you a review gate before any code is written. See the Task Plans guide for the full lifecycle and tips.

---

Step 7 — Set up the database (optional)

If your project uses a database, the Database Setup step can automatically create the schema from the generated code:

1. Click Database Setup in the agent pipeline (unlocks after development completes).
2. Enter your database connection string.
3. Choose the database type (or use Auto-detect).
4. Optionally enable Include seed data for realistic test fixtures.
5. Click Setup Database and wait for the three-step progress tracker to complete.

The result shows tables created, indexes applied, and any warnings. See the Database Setup guide for troubleshooting.

---

Step 8 — Capture lessons learned

The Lessons Learned accordion at the bottom of the Development Board lets you record insights about each repository:

• Click the Lessons Learned header to expand.
• Click + next to a repository to add a lesson.
• Edit or delete existing lessons inline.
• Lessons are injected as context for all future agent calls on that project — the AI will respect constraints and patterns you’ve documented.

Examples of useful lessons:

Always use the existing RedisClient singleton from src/lib/redis.ts
The payment module is handled by a third-party team — do not modify it
All new endpoints must include OpenAPI JSDoc annotations

---

What’s next?

• Dive deeper with the Task Queue guide for tips on writing effective task requests.
• Use Task Plans for complex multi-file changes.
• Use Content Mode to generate release changelogs from your commits.
• Ready to ship? Use Deploy Mode to push your changes to production.