Services for AI startups and AI product teams
Automation for AI companies: the operations around your model, handled
Make It Flow builds automated business solutions for AI startups and AI product teams: a CRM that turns signups into a sales pipeline, LLM evaluation that runs on every prompt or model change, an AI support agent for your API docs, usage and billing anomaly alerts, security questionnaire drafts, release notes and a change log, and a website built to be cited by AI search. Your engineers keep shipping; people approve every claim and every customer-facing change.
Your stack stays yours
Workflows run in your own n8n instance, cloud account or repository, under your API keys. We hand over every workflow, prompt and evaluation set, so nothing is locked to us.
Claims are checked by people
Automation drafts questionnaire answers, release notes and support replies from approved sources. A person approves anything that makes a claim about your model, your data handling or a customer's account.
Built for the rules you sell into
We design with the EU AI Act transparency and general-purpose model duties, the voluntary NIST AI Risk Management Framework and privacy law in mind, and keep a record of what changed, when and who approved it.
Services
Automation for AI companies, built around your product.
Case Study
Case Study: AI Startup Evals, Billing & Sales Automation
We built a connected set of automations for an AI startup selling an API and an enterprise plan: a signup-to-sales CRM pipeline, an LLM evaluation pipeline in CI, usage and billing anomaly alerts, security questionnaire drafting and release notes with a model change log. Engineers now see regressions before merging, the founder sees qualified accounts in Slack, and questionnaires no longer eat their evenings.
- Input
- Logic and services
- AI step
- Data
- People
- Output
What changed for the practice
- Prompt and model changes are evaluated before they merge, and regressions show up on the pull request.
- The founders see growing accounts in Slack with usage history instead of at invoice time.
- Unusual usage is caught within hours and discussed with the customer before the invoice.
- Questionnaires start from approved drafts, and answers stay consistent between deals.
- Every release has notes and a change log entry linked to its evaluation evidence.
Platform integrations
The software you already use, connected.
HubSpot
CRMContacts, companies, deals and pipeline stages for signups and enterprise deals.
HubSpot CRM REST API.
Attio
CRMRecords, lists and usage attributes for product-led sales.
Attio REST API and webhooks with scoped tokens.
Salesforce
CRMAccounts, opportunities and usage fields for larger sales teams.
Salesforce REST API, confirmed per project.
Stripe
BillingUsage meters, subscriptions, usage threshold alerts and invoices.
Stripe API and webhooks.
GitHub
Code and CIPull requests, labels, deployments and evaluation jobs.
GitHub REST API and GitHub Actions.
GitLab
Code and CIMerge requests and evaluation jobs.
GitLab API and GitLab CI, confirmed per project.
Tools we built
Free tools we built and use every day.
The Make It Flow platform
Website audits, monitoring and reports
- AI Search Readiness FreeCheck access for Google AI, Copilot, ChatGPT and Perplexity bots
- SEO Audit FreeTitles, meta, headings, indexability, sitemaps and schema
- Website Security Scan FreeSSL, security headers, cookies and exposed file checks
- Email Deliverability Check FreeMX, SPF, DKIM, DMARC, MTA-STS and BIMI with ready DNS fixes
- Website Monitoring Scheduled re-scans, score emails and 5-minute uptime alerts
- Technology Detection FreeSee the CMS, frameworks and analytics tools behind any website
Free website tools for practices
How we deliver
Agile delivery, in 1 to 2 week sprints.
Every sprint
- 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
- 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
- 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
- 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.
How scope stays under control
- Product backlog
- Every feature, fix and question in one prioritised list you can see at any time.
- Acceptance criteria
- Plain-language conditions for "done" on each item, agreed before work starts.
- Change requests
- New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
- User acceptance testing (UAT)
- Before launch your team tests the real workflow against the acceptance criteria and signs off.
Tools we use
Project manager / Scrum master
Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.
Business analyst
Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.
Automation engineer
Builds the n8n workflows, integrations, AI steps and error handling.
Backend developer
Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.
Frontend / mobile developer
Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.
QA engineer
Tests every workflow against the acceptance criteria, including edge cases and failure paths.
DevOps engineer
Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.
Who does what at each phase
- Free call
- Project manager, business analyst
- Understand the problem, check it is worth automating and outline a rough range.
- Discovery
- Business analyst, automation engineer
- Map the current process, systems and data, and agree success measures.
- Design
- Business analyst, automation engineer, backend developer
- Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
- Sprints
- Automation engineer, developers, QA
- Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
- UAT and launch
- QA, DevOps, project manager
- Your team tests and signs off, we switch on, monitor closely and train the team.
- Support
- Automation engineer, DevOps
- Stabilisation window, then optional monthly care with monitoring and changes.
A point of contact
One person who can answer questions and approve decisions, with about an hour a week during the project.
Access
Admin or API access to the systems involved, created as separate accounts with the least access needed.
Sample data
Real but non-sensitive records (or de-identified ones) so we can design and test against reality.
Approved wording
Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.
Vendor agreements
Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.
Time for testing
A few hours from the people who will use the system, for the demos and user acceptance testing.
Working system
Workflows, integrations and any apps running in your accounts, under your keys.
Documentation
Workflow specification, data-flow map, run book and exported workflow files.
Training
A walkthrough for the team and a short recorded video for new starters.
Handover
All access, credentials and code handed over; you can keep us or take it in-house.
Stabilisation window
Fixes for anything that does not meet the agreed acceptance criteria after launch.
Support options after launch
No plan
You run it yourselves after the stabilisation window and contact us when you need a change.
Monthly care
Monitoring, error alerts, small changes and updates each month, with an agreed response time.
Priority care
Faster response times for business-critical workflows and a monthly review call.
How a project moves through our team
- Input
- Logic and services
- People
- Output
- Data
How it flows
- 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
- 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
- 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
- 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.
Tech we work with
Any language, any stack.
Make It Flow delivers automated business solutions: workflows, integrations, AI assistants and the apps around them. Our team works in whatever language and stack fits the job and the systems you already run.
Automation
Backend
Data
Frontend and mobile
AI
Cloud and DevOps
Guides for ai companies
-
AI Startup Website Checklist: Crawlers, Trust Pages and UK RulesGuides · 10 min read
-
LLM Evaluation Workflow: Tracking Regressions on Every ChangeAutomation · 8 min read
-
What Are AI Agents? A Plain-English Guide for Small BusinessesAutomation · 10 min read
-
Claude Referral Traffic Is Rising: How to Get Cited by ClaudeSEO · 9 min read
-
Block or Allow AI Crawlers? GPTBot, ClaudeBot and MoreSEO · 10 min read
-
What Is llms.txt and Do I Need One for My Website?Guides · 7 min read
-
Support Ticket Triage and Release Notes: A Workflow for Software CompaniesAutomation · 10 min read
-
SaaS SEO Checklist: 12 Fixes for Software Company WebsitesSEO · 10 min read
FAQ
Automation for AI companies answered.
Usually the work around the product rather than the product itself: routing signups into a sales pipeline, running evaluations when prompts or models change, answering repeat API questions, catching usage spikes and drafting security questionnaire answers. Each is a contained workflow that frees engineers without touching the model.
Our fixed quotes start at $1,000 to $2,500 per workflow, $2,500 to $7,500 for an AI support agent and $5,000 to $15,000 for a website. A connected set of five workflows typically lands between $5,000 and $12,500. Your CRM, Stripe, n8n, evaluation tools and model usage are billed to you by each vendor.
Yes. HubSpot, Attio or Salesforce for CRM; Stripe for usage-based billing; GitHub or GitLab, promptfoo and Langfuse for evaluations; Intercom or Zendesk for support; Linear or Jira for issues; Slack for alerts. We confirm API access before quoting.
This hub covers automation around your product. If you need model work, such as a custom classifier or a small fine-tuned model, we scope it separately as machine learning after a discovery call.
Yes, remotely and worldwide. In the EU, Article 50 of the AI Act sets transparency duties from 2 August 2026 and Article 53 sets duties for general-purpose model providers from 2 August 2025; we design records and disclosures with those in mind.
A single workflow usually goes live in three to five weeks. A connected set is delivered in one-week Scrum sprints, one workflow at a time, in about eight weeks.
Free 20-minute call
Tell us what slows your team down
Book a free 20-minute call. We look at your signups, evals, support queue, billing and the questionnaires piling up, tell you honestly which parts are worth automating and give you a fixed quote for the first workflow.
Sources we checked
Rules and product facts on this page come from these pages, checked in November 2026. This is general information, not legal advice; confirm the rules that apply to your practice with your own adviser.
- EU AI Act, Article 50 (transparency)
- EU AI Act, Article 53 (general-purpose AI model providers)
- NIST AI Risk Management Framework
- GDPR Article 28 (processors)
- FTC: CAN-SPAM Act compliance guide
- UK PECR regulation 22
- W3C WCAG 2.2
- Stripe: usage-based billing (incl. usage monitoring alerts)
- promptfoo: GitHub Action
- promptfoo: CI/CD integration
- Langfuse: clarifications (MIT core, self-hosting)
- Langfuse documentation
- Attio REST API
- Zendesk Ticketing API
- Intercom developer FAQs
- Linear API and webhooks
- Drata: public API updates for questionnaire tracking
- Vanta: questionnaire automation
- n8n pricing
- n8n self-hosting
- Google autocomplete phrasing checked for keywords (llm evaluation, security questionnaire automation, stripe usage based billing, ai support agent, ai startup website, release notes automation)