Skip to main content
Prompt chaining means breaking one big task into smaller steps. Instead of asking the AI to do everything at once, you guide it through each step, using what you learned from the previous step to inform the next one. Think of it like training a junior associate. You wouldn’t say “review this contract.” You’d say “first find the payment terms, then check if they’re standard, then draft alternatives for any problems.”

​
Why Chaining Works

When you try to do everything in one prompt, the AI gets overwhelmed and misses details. Breaking tasks into steps gives you:
  • Better accuracy because the AI focuses on one thing at a time
  • Visibility into the AI’s thinking at each stage
  • The ability to correct course if something goes wrong
  • Reusable workflows you can apply to similar documents

​
The Basic Approach

After each AI response, you make a decision: continue to the next step, refine what you got, or change direction entirely. You’re in control at every stage.

​
Three Core Techniques

  1. ​
    Sequential Chain

Move through steps in order, where each step uses information from the previous one. This works best for standard reviews where you know what you’re looking for.

  1. ​
    Forked Chain

Generate multiple options first, then analyze them. Example: “Draft three different liability caps, then tell me the pros and cons of each.” This helps when you need to explore different approaches before choosing one.

  1. ​
    Loop and Refine

Keep improving the same output until it’s right. Start with: “Summarize these risks” Then: “Make it simpler for executives” Then: “Add business impact for each risk” Keep going until you have exactly what you need.

​
Clause Review

  1. Extract the relevant clause
  2. Summarize what it says
  3. Identify the risks
  4. Suggest better language

​
Risk Analysis

  1. List all potential risks
  2. Rank them by importance
  3. Explain why each matters
  4. Suggest how to fix them

​
Negotiation Prep

  1. Find the problematic terms
  2. Group by how hard to negotiate
  3. Create fallback positions
  4. Format for management review

​
Building Your Own Chains

​
The Standard Template

Most legal review chains follow this pattern: 
Step 1: Background
Tell the AI what kind of deal this is and your role

Step 2: Task
What to find or analyze

Step 3: Risk Review
Evaluate what was found

Step 4: Action
Create the output you need

​
Making Chains Work Better

  • Keep steps focused. Each prompt should do one clear thing.
  • Reference previous steps explicitly. Say “Using the risks you just identified…” not just “Using the risks…”
  • Label your steps. Use “Step 1:” or ”## Analysis Phase” to keep things organized.
  • Save successful chains. When a chain works well, save it for next time.
  • Start fresh if things go wrong. If the AI gets confused, don’t try to fix it. Begin again with clearer instructions.
  • Get reasoning before edits. First understand the problems, then work on solutions.

​
When to Use Chains

​
Use Chains For:

  • Complex documents with multiple issues
  • Tasks where you need to see the thinking process
  • Situations where you might need to adjust your approach
  • Work requiring multiple perspectives
  • Anything you’d normally do in stages yourself

​
Skip Chains For:

  • Simple, routine tasks
  • Standard playbook applications
  • Quick yes/no questions
  • When you know exactly what output you need

​
Common Problems

  • The chain drifts off topic: Start over with clearer first step.
  • The AI forgets earlier context: Begin each step with “Based on the above…” or similar reminder.
  • Quality varies between steps: Add a quick verification between major stages.
  • Too many steps: If you need more than 5-6 steps, you might be overcomplicating. Combine related steps.

​
A Complete Example

Here’s how to review an amendment: 
Step 1: "What terms are changing from our original agreement?"

Step 2: "Why might they want each of these changes?"

Step 3: "Which changes create new risks for us?"

Step 4: "Write an email accepting the low-risk changes but proposing alternatives for the risky ones."
Each step builds on the last, creating a complete review process.

​
The Key Insight

Chaining isn’t just about breaking things down. It’s about creating a repeatable process that matches how you actually think through legal problems. Once you have a good chain, you have a workflow you can use every time you face a similar task. Don’t expect AI to nail a complex review in one shot, just like you wouldn’t expect that from a new team member. Guide it through your process step by step, and you’ll get professional results.