Updated November 2026 · Written and maintained by the Progression Agency strategy team
AI in software development now runs from a suggestion that finishes a line to an agent that reads a repository, edits files, runs the tests and opens a pull request on its own. The speed is real, and so is the new work it creates: someone still has to read every change, check every package it adds and decide what ships. This page follows one change from ticket to production and marks where AI helps, where an agent can act alone and where a person signs off. Progression’s own developers use these tools on client builds, and the team is based in New York.
On this page · 14 sections
- A pull request that passed every test
- What AI in software development covers now
- What is agentic software development?
- AI assisted software development, step by step
- How the work shifts in each phase of the life cycle
- Reviewing AI-written code
- Which packages should an assistant be allowed to add?
- Security for code written with AI
- Who owns code written with AI?
- Keeping code, keys and data where they belong
- AI tools for software development, sorted by job
- How to use AI in software development on an existing codebase
- How Progression’s developers use AI
- What AI-assisted builds cost
Want AI inside your product instead? Building AI features that your users touch is a different job, covered on our AI app development page.
Examples marked “Illustrative example.” are hypothetical, and no real codebase, company or person is shown.
A pull request that passed every test
Picture a hypothetical team that hands a coding agent a small task: add a CSV export to the reports screen. Twenty minutes later a pull request arrives. Every test is green, the export works, and the diff touches fourteen files.
The reviewer who read all fourteen files found three things no test was written to catch: a date library added for one line of formatting, an API key pasted into a test fixture, and a database role quietly widened to write access so a query would run. None of them broke the build. All of them would have shipped.
- Tests prove the code does what the tests ask, nothing more.
- An agent optimizes for finishing the task it was given.
- A person reads for what the task never mentioned.
What AI in software development covers now
Three working modes sit under the same label, and they hand over very different amounts of work. GitHub’s documentation for Copilot in the editor lists all three: suggestions as you type, chat about the codebase, and an agent mode that finds relevant code, edits files, runs commands and validates its own work while you review and redirect it.
| Mode | What the AI does | What the developer does | Typical risk |
|---|---|---|---|
| Suggestions | Completes the line or block being typed | Accepts, edits or rejects each one | Plausible code that is subtly wrong |
| Chat | Explains code, compares approaches, drafts snippets | Asks, judges and pastes what fits | Confident answers about code it has not read |
| Agent in the editor | Finds code, edits files, runs commands, checks its work | Watches, redirects, reviews the changes | Wide edits across many files |
| Cloud agent | Works a task in a remote environment and opens a pull request | Writes the task, reviews the pull request | Changes nobody watched being made |
| AI code review | Comments on a pull request | Weighs the comments, still reads the diff | Missed issues read as approval |
The same tools now reach past the editor. On the code host, Copilot can plan and make changes, review pull requests and automate repository tasks, and you can request a review from it on a pull request like any other reviewer.
What is agentic software development?
It is development where an AI agent carries a task through several steps on its own: reading the code, deciding what to change, editing files, running commands and checking the result, then handing back a finished change for a person to review. Anthropic describes Claude Code in the same terms, as an agentic coding tool that reads your codebase, edits files, runs commands and integrates with your development tools.
- The unit of work is a task, not a line.
- The agent decides the order of steps.
- It runs real commands, so its environment matters.
- Its output is a diff or a pull request for a person to judge.
Sessions, sandboxes and permissions
GitHub separates three things worth separating in any setup: the client you talk to the agent through, the session that holds the conversation and its activity, and the environment where the agent actually executes, such as a cloud sandbox, a GitHub Actions runner or a remote custom environment. The environment decides what the agent can touch. Give it the repository and the test database, never production credentials, and make anything outside that a request a person approves.
AI assisted software development, step by step
A change still moves through the same gates it always did. What changes is who does the first draft at each gate and how closely a person checks it.
- Write the ticket with what done looks like, including what must not change.
- Let chat or an agent propose a plan, and approve it before code exists.
- Run the agent in a sandbox with the tests and nothing more.
- Let automated checks run on every push: tests, static analysis, dependency scans.
- Read the full diff, line by line, before anything merges.
- Release in stages and watch the numbers that matter.
In AI assisted software development the cheapest place to catch a mistake moves earlier: a plan that is wrong costs a minute to reject, while a fourteen file diff built on that plan costs an hour to unpick.
How the work shifts in each phase of the life cycle
The phases themselves do not change; our guide to the software development life cycle sets them out. The table shows how AI in the software development life cycle redistributes the work within each one.
| Phase | What assistants help with | What agents can take on | What a person keeps |
|---|---|---|---|
| Planning | Summarize tickets and past decisions | Draft task breakdowns | Priorities and scope |
| Requirements | Turn notes into user stories | Spot gaps against existing code | What the business actually needs |
| Design | Compare approaches and tradeoffs | Sketch interfaces and data models | Architecture and security design |
| Development | Complete code, explain unfamiliar parts | Implement scoped tasks end to end | Approval of every merged line |
| Testing | Suggest test cases and edge cases | Write and run tests, fix failures | Whether the tests prove the right thing |
| Deployment | Explain pipeline errors | Draft pipeline and config changes | Release decisions and access to production |
| Maintenance | Read logs and stack traces | Propose fixes and dependency updates | Which fixes ship, and when |
Which phase gains the most?
Development and testing, because the work there is concrete and checkable: code compiles or it does not, and a test passes or fails. Planning and design gain less, since their outputs are judgments that an assistant can inform but not settle.
Reviewing AI-written code
NIST’s Secure Software Development Framework asks teams to decide when to use code review, where a person looks directly at the code, and code analysis, where tools find issues either fully automated or alongside a person. Code from an assistant needs both, aimed differently.
- Peer review of every change, with earlier analysis and test results in front of the reviewer.
- Expert reviewers looking for backdoors and other malicious content in sensitive areas.
- Static analysis run automatically against the team’s coding standards.
- Every issue found recorded and triaged in the team’s tracker, not left in a chat.
Why a passing test suite is not a review
Tests check the behavior someone thought to test. An agent that writes both the code and its tests can make them agree with each other and still miss what the task meant. The SSDF also suggests adding a test for each previously reported vulnerability so the same error cannot come back, a habit that matters more when code arrives faster.
Should AI review AI-written code?
As a first pass, yes. An AI reviewer comments quickly on every pull request and catches common slips. Treat its comments as one more input, and keep a person’s approval as the condition for merging.
Which packages should an assistant be allowed to add?
Assistants reach for libraries freely, and every new package is code your team now ships and maintains. The SSDF’s guidance on third-party components applies unchanged: acquire well-secured components, check them for publicly known vulnerabilities, and make sure each one is still maintained and has not reached end of life.
- Confirm the package exists under the exact name suggested, from the expected publisher.
- Ask whether the standard library or an existing dependency already does the job.
- Check open vulnerabilities and the date of the last release.
- Read the license before the package reaches the main branch.
- Pin versions, and let automated scans watch them afterward.
Security for code written with AI
Two public references cover most of the ground. NIST published SP 800-218A in July 2024, an SSDF profile that adds practices for generative AI and dual-use foundation models across the life cycle, written for producers of AI models, producers of systems that use them, and organizations that acquire those systems. It is used together with the original SSDF.
The OWASP Top 10 for Large Language Model Applications identifies the most critical security vulnerabilities in applications built on large language models, and the project has grown into the OWASP GenAI Security Project, which also covers agentic AI systems. Generative AI for software development sits in both worlds: it is a tool that writes code, and an AI system with its own weaknesses.
- Treat text an agent reads from issues, web pages and files as untrusted input, not instructions.
- Keep secrets out of prompts, context files and repositories an agent can read.
- Limit the commands and network access an agent has without asking.
- Log what each agent session changed and which account it ran under.
Software to build this year?Describe the product and the deadline. You get a free proposal with the scope, the team and the price.
Get a free proposalTell us about a project you’d like help with.
Who owns code written with AI?
The U.S. Copyright Office answered the core question in Part 2 of its AI report, published January 29, 2025. Outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements.
- A human-authored work that is perceptible in the output can be protected.
- Creative arrangements or modifications of the output by a person can be protected.
- The mere provision of prompts is not enough.
- Using AI to assist, or including AI material in a larger human work, does not bar protection of the human contribution.
The Office’s copyright and AI page tracks the rest of the series, including Part 3 on training AI models, released in pre-publication form on May 9, 2025. For a software owner the practical step is a record: who designed the system, which parts people wrote or substantially reworked, and how AI output was selected and changed. Contracts with any development team should also say plainly who owns the code and how AI tools may be used on it.
Keeping code, keys and data where they belong
The SSDF asks that all code be stored on the principle of least privilege, so only authorized people, tools and services can reach it, and that every change be tracked to an individual account. Agents count as tools under that rule.
- Give each agent its own identity, so its commits are attributable.
- Scope repository access to the projects the task needs.
- Check where each tool sends code and whether the vendor keeps it.
- Store keys in a secrets manager, never in fixtures or configs.
- Review the access an agent holds as often as you review a person’s.
AI tools for software development, sorted by job
Product names change faster than the jobs they do. Sorting AI software development tools by where they run and what they touch makes the adoption questions clearer.
| Tool type | Where it runs | Good for | Check before adopting |
|---|---|---|---|
| Editor assistant | Inside the code editor | Suggestions, chat about open files, agent mode | What code leaves the laptop, and who keeps it |
| Terminal agent | The developer’s command line | Multi-file tasks, running and fixing tests | Which commands it may run without asking |
| Cloud coding agent | A remote sandbox or CI runner | Background tasks that end in a pull request | Which secrets and networks the environment can reach |
| Pull request reviewer | The code host | First pass comments on every change | That a person still approves the merge |
| Chat assistant | A browser or desktop app | Explaining, drafting, rubber duck debugging | Pasting code under the company’s data rules |
| Test generator | Editor or CI | Filling coverage gaps | Tests that assert behavior, not just run lines |
Tool choices for app teams, from editors to cloud backends, are covered on our app development tools page, and no-code builders on our low-code app development page.
AI in mobile app development
Mobile adds checks an assistant cannot run on a laptop alone: real devices, store review rules and platform permissions. AI in mobile app development speeds the screens and data models; device testing and the store submission still need a person who knows both platforms. See our iOS app development and Android app development pages.
How to use AI in software development on an existing codebase
Older code is where assistants help most and where agents can do the most damage, because the reasons behind odd choices are rarely written down. If you want engineers who already work this way, our page on how to hire AI developers sets out the skills to test and the ways to engage them.
- Start with reading: ask chat to explain modules before anyone changes them.
- Write tests around the behavior you must keep, with AI help, before refactoring.
- Hand agents small, bounded tasks with a clear finish line.
- Add instruction files that tell agents the conventions and the no-go areas.
- Widen the scope only after a run of clean reviews.
Teams moving an old system forward often pair this with DevOps work on the pipeline, so every agent change meets the same automated checks as a person’s.
How Progression’s developers use AI
Progression’s own developers use AI coding tools on client builds, inside the same delivery process as hand-written work. Generated code goes through the same review, security checks and testing as code a person typed, and nothing merges before that.
- Two-week sprints with automated tests and code review.
- Releases through CI/CD pipelines with staged rollouts.
- AI-written changes reviewed like any other change before merge.
- Clients own the code they pay for.
The wider build work is described on our software development company, MVP development and AI agent development pages.
What AI-assisted builds cost
AI in software development speeds parts of the work, but scope, integrations and review still set the price. The bands below run from the typical low to the published high in the US market.
| Build | Typical low to published high | Notes |
|---|---|---|
| US development team, hourly | $100 to $200 an hour | Agency or contract bill rate |
| App MVP | $15,000 to $80,000 | Single or cross-platform, core flows |
| Integration or internal tool | $30,000 to $100,000 | One integration or one workflow |
| SaaS MVP | $30,000 to $150,000 | First paid version of a product |
| Mid complexity app | $60,000 to $150,000 | Payments, integrations, admin panel |
| Portal or platform | $75,000 to $400,000 | Multi-role business systems |
Progression’s price is set in the written proposal, after scope, and is subject to change. Our app development cost guide breaks the bands down further.
Does AI make custom software cheaper?
It can shorten the drafting, and it adds review, security and testing work that cannot be skipped. The saving shows up most on well-defined tasks in a well-tested codebase, and least on new architecture or unclear requirements.
What this page leaves out: the Progression Method, proprietary and reserved for clients. Reach out to learn more
Getting found in search
AI, AEO and what is changing
Paid media and lead generation
Websites and design
Choosing and working with an agency
Software and app development
Website design by industry and type
Web development, platforms and hosting
Social, content and brand
By industry and by situation
Pricing depends on scope and is confirmed in a written proposal. Published prices are subject to change.
Frequently asked questions
What does AI in software development do day to day?
How would you define AI assisted software development?
How does a coding assistant differ from a coding agent?
Can an AI agent open a pull request by itself?
Should AI review AI-written code?
What does NIST say about code review?
How do you check a package an assistant suggests?
Is there a security framework for generative AI development?
What is the OWASP Top 10 for LLM applications?
Can code written with AI be copyrighted?
Does writing prompts make me the author of the code?
Does using AI stop the rest of my code being protected?
Is my code sent to the AI vendor?
Where should a coding agent run?
Can ChatGPT create apps?
Does AI replace developers on a project?
Which phase gains most from AI in software development?
How do we start using AI on an old codebase?
How does Progression’s team use AI on client work?
Does AI make custom software cheaper?
What does an AI-assisted build cost?
Software to build this year?Describe the product and the deadline. You get a free proposal with the scope, the team and the price.
Get a free proposalTell us about a project you’d like help with.
Get a free marketing proposal
Tell us what you are trying to grow and we will come back with a plan, not a pitch deck. Same-day reply on weekdays.
