Skip to main content
MethodTechnology & DevelopmentApp & web developmentIntermediate

Choose a technology stack

A reasoned stack recommendation comparing options against your requirements, team and budget.

This is a practical, copy-paste process for starting a new product.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# Choose a technology stack
Method by Deepstory Research: deepstoryresearch.com/method/tech-stack-selection

You are a pragmatic CTO. Follow the method below step by step. Goal: A reasoned stack recommendation comparing options against your requirements, team and budget.

## My inputs
- Product and requirements: [PRODUCT_AND_REQUIREMENTS]  (example: B2B dashboard with real-time data)
- Team skills: [TEAM_SKILLS]  (example: TypeScript, Python)
- Scale expectations: [SCALE_EXPECTATIONS]  (example: 10k users year 1)
- Budget: [BUDGET]  (example: modest cloud spend)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. List requirements that constrain the choice.
2. Compare 2–3 stacks (frontend, backend, database, hosting, auth).
3. Score on fit, team skill, cost, ecosystem and lock-in.
4. Recommend one with a migration escape hatch.

## Deliver the output in this structure
- Requirements
- Options comparison
- Recommendation
- Risks
- First steps

## Quality rules
- Prefer boring, well-supported technology unless there is a strong reason.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

InputPlaceholderExample
Product and requirements[PRODUCT_AND_REQUIREMENTS]B2B dashboard with real-time data
Team skills[TEAM_SKILLS]TypeScript, Python
Scale expectations[SCALE_EXPECTATIONS]10k users year 1
Budget[BUDGET]modest cloud spend

Use it when

  • Starting a new product.
  • Replatforming.

What you get

  • Requirements
  • Options comparison
  • Recommendation
  • Risks
  • First steps

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    List requirements that constrain the choice.

  2. 2

    Compare 2–3 stacks (frontend, backend, database, hosting, auth).

  3. 3

    Score on fit, team skill, cost, ecosystem and lock-in.

  4. 4

    Recommend one with a migration escape hatch.

Quality checks built into the prompt

  • • Prefer boring, well-supported technology unless there is a strong reason.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

EvidenceAI Models

GLM-5.2 Benchmarks

How Z.ai’s GLM-5.2 stacks up against the frontier (Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro) and its predecessor GLM-5.1 — across long-horizon coding, standard coding, reasoning, and agentic benchmarks, plus the MTP speculative-decoding gain. The strongest open-source model at launch.

Run next

Methods that chain well after this one.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.