# pair\_programming

Pair programming is a software development practice in which two programmers collaboratively work on the same code, typically at one computer.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## I Run a One-Person Company With AI. Here's What I Won't Let It Do

DevFeed: [I Run a One-Person Company With AI. Here's What I Won't Let It Do](<https://devfeed.tech/articles/i-run-a-one-person-company-with-ai-here-s-what-i-won-t-let-it-do-131613.md>)

Original publisher: [Read original article](<https://hackernoon.com/i-run-a-one-person-company-with-ai-heres-what-i-wont-let-it-do?source=rss>)

Author: sammii

Published: 2026-11-13T07:05:53Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attention](<https://devfeed.tech/tags/attention.md>), [authorship](<https://devfeed.tech/tags/authorship.md>), [brand](<https://devfeed.tech/tags/brand.md>), [branding](<https://devfeed.tech/tags/branding.md>), [code](<https://devfeed.tech/tags/code.md>), [company](<https://devfeed.tech/tags/company.md>), [content](<https://devfeed.tech/tags/content.md>), [content-creation](<https://devfeed.tech/tags/content-creation.md>), [control](<https://devfeed.tech/tags/control.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [one-person-company](<https://devfeed.tech/tags/one-person-company.md>), [products](<https://devfeed.tech/tags/products.md>), [publishing](<https://devfeed.tech/tags/publishing.md>), [sales](<https://devfeed.tech/tags/sales.md>), [solo-founder](<https://devfeed.tech/tags/solo-founder.md>), [startup](<https://devfeed.tech/tags/startup.md>), [trust](<https://devfeed.tech/tags/trust.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

A solo founder says AI lets him build products and handle work beyond his skills, while his technical knowledge helps him catch systems that look right but miss the mark. He treats authorship as choosing what should exist and spotting gaps. His tools may draft, suggest, render, schedule, and propose changes, but a proposal or passed validation check never counts as approval: he must approve anything published in his name. A separate content rule forbids inventing events, even if fabricated moments might perform better. He writes these limits into his systems so they hold when he is tired, framing trust and human control as practical choices he can make.

### Source excerpt

How a solo founder uses AI agents to build products, automate work, and maintain human control over publishing, authorship, and trust.

## How Spec-Driven Development Helped an SAP Team Move 71% Faster

DevFeed: [How Spec-Driven Development Helped an SAP Team Move 71% Faster](<https://devfeed.tech/articles/how-spec-driven-development-helped-an-sap-team-move-71-faster-125753.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-spec-driven-development-helped-an-sap-team-move-71percent-faster?source=rss>)

Author: marian kamenistak

Published: 2026-11-10T05:00:02Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [ABAP](<https://devfeed.tech/topics/abap.md>), [jira](<https://devfeed.tech/topics/jira.md>), [lead time](<https://devfeed.tech/topics/lead-time.md>), [qualitygates](<https://devfeed.tech/topics/qualitygates.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [abap](<https://devfeed.tech/tags/abap.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [cycle-time](<https://devfeed.tech/tags/cycle-time.md>), [developer-productivity](<https://devfeed.tech/tags/developer-productivity.md>), [development](<https://devfeed.tech/tags/development.md>), [engineering-management](<https://devfeed.tech/tags/engineering-management.md>), [faster](<https://devfeed.tech/tags/faster.md>), [requirements-engineering](<https://devfeed.tech/tags/requirements-engineering.md>), [sap](<https://devfeed.tech/tags/sap.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [spec-driven-development](<https://devfeed.tech/tags/spec-driven-development.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

An 18-person SAP team reported that median implementation cycle time fell from 19 days to about 5.5 over five weeks, while SLA-related resolution time fell 49%. The author says the team credited spec-driven development most, but notes the spec gate, shared AI skills, pairing, and an incident agent launched during the same period, so their individual effects cannot be separated. The team scored Jira specifications against a 10-point SAP rubric and returned any score below 8 with missing items; its initial average was 3.3. Once specs improved, shared skills helped locate relevant code contracts and bugs. An incident categorization agent took three hours to build, but support staff still manually categorize 20% of tickets with low-confidence results. Suggested starting steps are to establish a Jira cycle-time baseline, score 20 older specs, set the score-8 gate, and provide developers a shared setup and AI buddy pairing.

### Source excerpt

An 18-person SAP team cut median cycle time from 19 to about 5.5 days in five weeks. What helped most, by its own account: scoring every spec before any ABAP.

## Locating the source of a mysterious beep with Claude

DevFeed: [Locating the source of a mysterious beep with Claude](<https://devfeed.tech/articles/locating-the-source-of-a-mysterious-beep-with-claude-125090.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Nov/9/mysterious-beeps/>)

Author: Simon Willison

Published: 2026-11-09T23:57:21Z

Content type: article

Language: en

Sources: [Simon Willison](<https://devfeed.tech/sources/simon-willison.md>), [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [PWA](<https://devfeed.tech/topics/pwa.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-2-317](<https://devfeed.tech/tags/ai-2-317.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-327](<https://devfeed.tech/tags/claude-327.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-135](<https://devfeed.tech/tags/claude-code-135.md>), [claude-mythos-fable](<https://devfeed.tech/tags/claude-mythos-fable.md>), [claude-mythos-fable-47](<https://devfeed.tech/tags/claude-mythos-fable-47.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-agents-266](<https://devfeed.tech/tags/coding-agents-266.md>), [devices](<https://devfeed.tech/tags/devices.md>), [found](<https://devfeed.tech/tags/found.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-2-056](<https://devfeed.tech/tags/generative-ai-2-056.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-2-020](<https://devfeed.tech/tags/llms-2-020.md>), [location](<https://devfeed.tech/tags/location.md>), [projects](<https://devfeed.tech/tags/projects.md>), [projects-564](<https://devfeed.tech/tags/projects-564.md>), [python](<https://devfeed.tech/tags/python.md>), [room](<https://devfeed.tech/tags/room.md>), [server](<https://devfeed.tech/tags/server.md>)

### AI overview

Beep Locator used several browser-connected devices to triangulate an intermittent beep, locating it to about 40 cm and helping the author find an old carbon monoxide detector with depleted batteries. A Python web server coordinated listeners over WebSockets; each requested microphone access, kept a 60-second audio buffer, and detected candidate beeps using an FFT and high-pass filter. For a reported beep, the server triggered a short chirp and collected audio clips around it so recordings could be aligned for localization. Automatic sound-based device positioning proved unreliable, so the author added a rough mode for manually placing listener icons before sound-based adjustment. Clap detection and replaying clips helped test and identify the target beep; after confirmation, the system tracked its frequency and timing to refine the estimated location. The author also used a hot-swap mechanism to send updated code to listeners without reloading their pages.

### Source excerpt

Our house has a box room, full of boxes that we still haven't unpacked from our last move. A couple of weeks ago something in that room started intermittently beeping. The beeps were far enough apart that standing in the room and trying to determine the source of the noise was frustrating, and I really didn't want to dig through every one of those boxes. So I had Claude Code build Beep Locator, a software system for triangulating the source of a mysterious beep using multiple devices scattered around the room. Here's what Beep Locator looks like after it has been running for a while: You run Python web server to show the primary UI, and then use the QR code or URL to connect as many devices as you can spare to act as listeners - I was using two iPads, a phone, a MacBook Pro and a Surface Ultra. The devices then play noises to each other to help estimate their locations. This didn't work particularly well, so I added a "Rough mode" where you can drag their icons around in the space to provide rough locations which are then adjusted based on those sounds. Once that's set up, the devices all listen for the beep! I added a clapping mode too so I could test it by clapping my hands in different locations around the room - displayed as diamonds on the map. This helped me gain confidence that it was capable of locating a sound. Beeps show up on the map as an X, plus a line in the "Sounds located" log. You can replay these sounds (from each device in turn) to confirm they are the mysterious beep you are looking for, then click "This is the mystery beep" to mark them as such. Once you've confirmed the mysterious beep frequency the system will listen out for it, measure the interval between beeps, and use the triangulated locations to lock down the most likely location on the map. The system worked as intended. It gave me the position of the beep to within about 40cm, then I dug through that specific pile of boxes and found an ancient carbon monoxide detector that desperately

## TBM 450: The Loss of Positive Friction

DevFeed: [TBM 450: The Loss of Positive Friction](<https://devfeed.tech/articles/tbm-450-the-loss-of-positive-friction-122381.md>)

Original publisher: [Read original article](<https://cutlefish.substack.com/p/tbm-450-the-loss-of-positive-friction>)

Author: John Cutler

Published: 2026-11-07T23:03:14Z

Content type: opinion

Language: en

Sources: [The Beautiful Mess](<https://devfeed.tech/sources/the-beautiful-mess.md>)

Topics: [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [human centric design](<https://devfeed.tech/topics/human-centric-design.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [attention](<https://devfeed.tech/tags/attention.md>), [constraint](<https://devfeed.tech/tags/constraint.md>), [multiplayer](<https://devfeed.tech/tags/multiplayer.md>), [product-development](<https://devfeed.tech/tags/product-development.md>), [reflect](<https://devfeed.tech/tags/reflect.md>)

### AI overview

Constraints can both slow work and improve its outcome by creating time for reflection, shared understanding, and course correction. The author argues that removing product-development friction--such as ROI reviews, remote pairing, and multiple rounds of document revision--can also remove those benefits. AI tools can turn a customer-call transcript into deployed changes quickly, but that speed may bypass questions about customer intent, design durability, and whether the work is worthwhile. The practical takeaway is to deliberately make room for those checks and team reflection, especially as AI-assisted workflows make solo work and immediate output easier.

### Source excerpt

A constraint can be "enabling" and "limiting" at the same time.

## Pair Programming With AI Agents - How to Keep Learning While You Ship

DevFeed: [Pair Programming With AI Agents - How to Keep Learning While You Ship](<https://devfeed.tech/articles/pair-programming-with-ai-agents-how-to-keep-learning-while-you-ship-120873.md>)

Original publisher: [Read original article](<https://spin.atomicobject.com/pair-programming-ai-agents/>)

Author: Rebecca Rayford

Published: 2026-11-05T13:00:56Z

Content type: opinion

Language: en

Sources: [Atomic Object](<https://devfeed.tech/sources/atomic-object.md>)

Topics: [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [consulting](<https://devfeed.tech/tags/consulting.md>), [development-practices](<https://devfeed.tech/tags/development-practices.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [learning](<https://devfeed.tech/tags/learning.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

The author argues that AI agents can help developers ship while weakening their ability to explain and own their decisions when they replace the thinking that builds skill. Pairing helps retain that judgment: plan together before prompting, ask the agent to critique a human proposal, explain decisions aloud, and have a pair review prompts. The author also recommends using agents to map unfamiliar code, test a theory against the code before changing anything, guide a developer's own investigation, and explain each step in a checklist. The proposed test is whether each person can explain the work without the agent. The author presents shared prompt review as an experiment they have not yet tried.

### Source excerpt

When I was in Atomic Object's Accelerator program, I paired constantly. As I moved on to smaller projects and earned more trust, pairing slowly faded out of my day-to-day, and AI agents filled the gap. Then I was asked some specific questions about code I'd recently written. The code worked, but I couldn't explain why [...] The post Pair Programming With AI Agents - How to Keep Learning While You Ship appeared first on Atomic Spin.

## Trust Is the Binding Constraint

DevFeed: [Trust Is the Binding Constraint](<https://devfeed.tech/articles/trust-is-the-binding-constraint-109729.md>)

Original publisher: [Read original article](<https://newsletter.kentbeck.com/p/trust-is-the-binding-constraint>)

Author: Kent Beck

Published: 2026-10-30T13:02:54Z

Content type: release

Language: en

Sources: [Software Design: Tidy First?](<https://devfeed.tech/sources/software-design-tidy-first.md>)

Topics: [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Learning](<https://devfeed.tech/topics/learning.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-assisted-development](<https://devfeed.tech/tags/ai-assisted-development.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-workflow](<https://devfeed.tech/tags/ai-workflow.md>), [benefit](<https://devfeed.tech/tags/benefit.md>), [class](<https://devfeed.tech/tags/class.md>), [code](<https://devfeed.tech/tags/code.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [continuous-deployment](<https://devfeed.tech/tags/continuous-deployment.md>), [continuous-integration](<https://devfeed.tech/tags/continuous-integration.md>), [days](<https://devfeed.tech/tags/days.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [flow](<https://devfeed.tech/tags/flow.md>), [humanity](<https://devfeed.tech/tags/humanity.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [observability](<https://devfeed.tech/tags/observability.md>), [teams](<https://devfeed.tech/tags/teams.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

The author argues that AI speeds up code production while collaboration, testing, review, and shared understanding--the practices that build trust--risk being sacrificed. The advertised live class, The Human Practices Behind Trustworthy Software, presents XP practices such as testing, pairing, continuous integration, and observability as a system for building trust. It also advocates small, verified changes, arguing that code trustworthiness falls with the square of change size, and team-based AI development over solo work. The paid class runs November 9-10, with two-hour lectures and an hour of Q&A each day; sessions are recorded, and exercises are based on participants' teams. The author says it may not be useful for teams that already trust one another and have an effective AI workflow.

### Source excerpt

Teams accumulate code faster than they accumulate trust.

## Even with LLMs, Let's Pair Together

DevFeed: [Even with LLMs, Let's Pair Together](<https://devfeed.tech/articles/even-with-llms-let-s-pair-together-60929.md>)

Original publisher: [Read original article](<https://spin.atomicobject.com/llms-lets-pair-together/>)

Author: Patrick Pale

Published: 2026-09-28T12:00:34Z

Content type: opinion

Language: en

Sources: [Atomic Object](<https://devfeed.tech/sources/atomic-object.md>)

Topics: [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Product Management](<https://devfeed.tech/topics/product-management.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [context](<https://devfeed.tech/tags/context.md>), [critical](<https://devfeed.tech/tags/critical.md>), [development-practices](<https://devfeed.tech/tags/development-practices.md>), [downtime](<https://devfeed.tech/tags/downtime.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [models](<https://devfeed.tech/tags/models.md>), [pair](<https://devfeed.tech/tags/pair.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [programming](<https://devfeed.tech/tags/programming.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [team](<https://devfeed.tech/tags/team.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The author argues that pair programming remains valuable alongside LLMs in software development. Working with a colleague can encourage critical review of both generated code and how the team uses the tools, build shared understanding, and increase confidence in contributions.

### Source excerpt

For all the good and bad that has come with the LLM domination of software development recently, one aspect I can definitely appreciate is that everything feels on the table when it comes to figuring out how to best approach our jobs. Granted, that's also the part that terrifies me. It's definitely my and many [...] The post Even with LLMs, Let's Pair Together appeared first on Atomic Spin.

## Pair Programming With Your AI Agent

DevFeed: [Pair Programming With Your AI Agent](<https://devfeed.tech/articles/pair-programming-with-your-ai-agent-24913.md>)

Original publisher: [Read original article](<https://blog.blundellapps.co.uk/pair-programming-with-your-ai-agent/>)

Author: blundell

Published: 2026-09-06T21:50:09Z

Content type: article

Language: en

Sources: [Blundell](<https://devfeed.tech/sources/blundell.md>)

Topics: [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [androiddev](<https://devfeed.tech/tags/androiddev.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [antigravity-cli](<https://devfeed.tech/tags/antigravity-cli.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [development](<https://devfeed.tech/tags/development.md>), [driver](<https://devfeed.tech/tags/driver.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [geminicli](<https://devfeed.tech/tags/geminicli.md>), [intermediate](<https://devfeed.tech/tags/intermediate.md>), [intermediate-reference-ai-androiddev-gemini-geminicli-pairing](<https://devfeed.tech/tags/intermediate-reference-ai-androiddev-gemini-geminicli-pairing.md>), [keyboard](<https://devfeed.tech/tags/keyboard.md>), [local](<https://devfeed.tech/tags/local.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [navigator](<https://devfeed.tech/tags/navigator.md>), [pair](<https://devfeed.tech/tags/pair.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [ping-pong](<https://devfeed.tech/tags/ping-pong.md>), [programming](<https://devfeed.tech/tags/programming.md>), [reference](<https://devfeed.tech/tags/reference.md>), [terminal](<https://devfeed.tech/tags/terminal.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

The post frames working with a local AI coding agent as pair programming: you share a codebase, goal, and conversation, so the useful question is what kind of session you are having and who holds intent, the keyboard, and review. It maps four familiar styles to agent work: unstructured pairing has no assigned roles; Driver/Navigator separates hands-on implementation from review and direction; Strong-Style routes each idea through the other participant's hands, so the person with the idea does not type; Ping Pong alternates test-driven turns, with one participant writing a failing test and the other making it pass and writing the next. Antigravity CLI is the concrete example, but the author says the approach is not specific to it. The excerpt also introduces Pair Development as including planning, research, and documentation reading, but ends before explaining it further.

### Source excerpt

This post explains how to treat a session with a local AI agent as a pair programming session, and how the four classic pairing styles map onto working with one. I'll use Antigravity CLI for the concrete examples, though nothing here is specific to it. Swap in whichever agent sits in your terminal. The idea [...] The post Pair Programming With Your AI Agent first appeared on Blundell.

## Extreme Programming remains relevant for building software teams in 2026

DevFeed: [Extreme Programming remains relevant for building software teams in 2026](<https://devfeed.tech/articles/extreme-programming-1999-2026-32325.md>)

Original publisher: [Read original article](<https://newsletter.manager.dev/newsletter/extreme-programming-1999-2026>)

Author: Anton Zaides

Published: 2026-08-18T06:01:00Z

Content type: opinion

Language: en

Sources: [Manager.dev](<https://devfeed.tech/sources/manager-dev.md>)

Topics: [Programming](<https://devfeed.tech/topics/programming.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Refactoring](<https://devfeed.tech/topics/refactoring.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Code review](<https://devfeed.tech/topics/code-review.md>)

Tags: [code](<https://devfeed.tech/tags/code.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [development](<https://devfeed.tech/tags/development.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [programming](<https://devfeed.tech/tags/programming.md>), [redesign](<https://devfeed.tech/tags/redesign.md>), [tdd](<https://devfeed.tech/tags/tdd.md>)

### AI overview

The author revisits Kent Beck's Extreme Programming after experiencing frustration with Scrum and the pressures facing modern engineering teams. The article argues that XP remains relevant because it combines five values, 14 principles, and numerous practices aimed at improving both software and team life, rather than reducing the methodology to TDD and pair programming alone.

### Source excerpt

A method created 30 years ago is still your best guide for building software

## Extreme Programming 1999-\>2026

DevFeed: [Extreme Programming 1999-\>2026](<https://devfeed.tech/articles/extreme-programming-1999-2026-116561.md>)

Original publisher: [Read original article](<https://www.manager.dev/newsletter/extreme-programming-1999-2026>)

Author: Anton Zaides

Published: 2026-08-18T06:01:00Z

Content type: article

Language: en

Sources: [Manager.dev](<https://devfeed.tech/sources/manager-dev.md>)

Topics: [bestpractice](<https://devfeed.tech/topics/bestpractice.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2021](<https://devfeed.tech/tags/2021.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [actions](<https://devfeed.tech/tags/actions.md>), [adjustment](<https://devfeed.tech/tags/adjustment.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-slop](<https://devfeed.tech/tags/ai-slop.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [best](<https://devfeed.tech/tags/best.md>), [building](<https://devfeed.tech/tags/building.md>), [building-software](<https://devfeed.tech/tags/building-software.md>), [created](<https://devfeed.tech/tags/created.md>), [guide](<https://devfeed.tech/tags/guide.md>), [programming](<https://devfeed.tech/tags/programming.md>), [software](<https://devfeed.tech/tags/software.md>)

### AI overview

The author argues that Extreme Programming remains useful for software teams working amid AI adoption, but its values, principles, and practices need to be applied with judgment. XP aims to improve both software and team life, connecting five values--communication, simplicity, feedback, courage, and respect--to practical methods through principles such as humanity, mutual benefit, and quality. The author highlights cross-functional teams, team continuity, sustainable work, and direct customer contact as especially relevant. They question applying pair programming or test-first programming universally, and argue that code and tests alone may not preserve necessary project knowledge. They also describe AI as making design easier while encouraging excessive scope, and warn that AI-written code and parallel work can strain quality, review capacity, and team well-being. The excerpt presents XP as a framework for evaluating practices, not a complete prescription for current AI-era work.

### Source excerpt

A method created 30 years ago is still your best guide for building software

## Spend More Time Talking to Humans

DevFeed: [Spend More Time Talking to Humans](<https://devfeed.tech/articles/spend-more-time-talking-to-humans-77929.md>)

Original publisher: [Read original article](<https://www.honeycomb.io/blog/spend-more-time-talking-to-humans>)

Author: Douglas Soo

Published: 2026-08-03T13:00:00Z

Content type: article

Language: en

Sources: [Honeycomb Blog](<https://devfeed.tech/sources/honeycomb-blog.md>)

Topics: [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>), [Self-organizing Team](<https://devfeed.tech/topics/self-organizing-team.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI Context Switching](<https://devfeed.tech/topics/ai-context-switching.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>)

Tags: [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-llms](<https://devfeed.tech/tags/ai-llms.md>), [context](<https://devfeed.tech/tags/context.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [llms](<https://devfeed.tech/tags/llms.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [teams](<https://devfeed.tech/tags/teams.md>), [teams-collaboration](<https://devfeed.tech/tags/teams-collaboration.md>)

### AI overview

LLM-assisted coding is shifting software engineers' time from implementation toward design, validation, and communication. The article describes the resulting context switching and workload for senior engineers, alongside junior engineers' uncertainty about how to build skills. It recommends reducing parallel work and context churn, pairing senior and junior engineers to share context and practice design and validation, and coordinating more across teams.

### Source excerpt

LLMs have reshaped the day-to-day work of software engineering, leaving senior engineers exhausted by context-switching and junior engineers unsure how to grow. The fix isn't a better prompt -- it's spending more time talking to humans: reducing context churn, pairing across seniority levels, and communicating more across teams.

## Tracking feedback with Claude Code

DevFeed: [Tracking feedback with Claude Code](<https://devfeed.tech/articles/tracking-feedback-with-claude-code-52451.md>)

Original publisher: [Read original article](<http://www.jackfranklin.co.uk/blog/claude-code-ai-feedback-skill/>)

Published: 2026-04-24T00:00:00Z

Content type: article

Language: en

Sources: [Jack Franklin](<https://devfeed.tech/sources/jack-franklin.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [To-Do](<https://devfeed.tech/topics/todo.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [debugger](<https://devfeed.tech/tags/debugger.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [game](<https://devfeed.tech/tags/game.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [markdown-files](<https://devfeed.tech/tags/markdown-files.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [tokens](<https://devfeed.tech/tags/tokens.md>), [tracking](<https://devfeed.tech/tags/tracking.md>), [ui](<https://devfeed.tech/tags/ui.md>)

### AI overview

For playtesting OnTrack, the author first used Claude Code to collect notes in Markdown, where Claude grouped feedback, detected duplicates, and refined related items. As the lists grew to thousands of lines, even simple queries required reading whole files. The author replaced that workflow with a custom skill backed by a Deno CLI and SQLite: records hold titles, details, priority, status, category, project, and a completion flag. Completed items remain available as history but are hidden from default listings. The skill guides Claude to list titles and IDs before fetching details, check for related feedback before adding items, and infer the project from context when clear. The excerpt says this made targeted backlog queries faster and more accurate; it does not provide broader performance measurements.

### Source excerpt

I've been using Claude Code as a pair programmer, debugger, and feedback collector while I playtest my game, OnTrack. The setup has worked so well that I ended up building a small custom skill to make it scale and in this post I'll take you through how it works. (That last DevBlog was in 2024 (!), but I have continued to work on the game -- with AI my pace and progress has quickened, even if overall I've less time since becoming a dad.) Pausing development to playtest After a period of development, I like to do a playtest. I resist fixing things, and instead I play the game for an hour, noting down bugs, thoughts and suggestions as I go. I used to do this in a Trello board, but I recently decided to try using Claude as my bug collecting coworker and collate feedback in a markdown file. This worked really well! One of the benefits of using Claude is that it was able to detect similar feedback, or duplicates, or re-write old feedback to incorporate new points that were related. It also grouped them as it went under different categories such as UI, mechanics, or "quick wins". The problem of large Markdown files As I then followed these playtesting sessions with fixes, I asked Claude to mark feedback as complete by moving it into a separate document. In one hour of playtesting I would easily pick up on 50+ issues I wanted to fix (the game is far from done!) and one day I realised that the Markdown file with incomplete items was 3,000 lines long, and the one with completed items was 4,000 lines long! Claude was managing this fine - but I could see that as time grew, this list would become hard to manage, eat up more of my tokens, and become inefficient. Asking Claude to list the outstanding issues, or all the issues under a particular category, required it to read the entire Markdown file, even if I was only asking about a subset. The solution: SQLite I needed a way to store this data in a more structured form where Claude could query it more efficiently -- for example, ge

## Ace: A Shared Workspace for Teammates and Coding Agents

DevFeed: [Ace: A Shared Workspace for Teammates and Coding Agents](<https://devfeed.tech/articles/one-developer-two-dozen-agents-zero-alignment-67186.md>)

Original publisher: [Read original article](<https://githubnext.com/talks/one-developer-two-dozen-agents-zero-alignment/>)

Published: 2026-04-09T00:00:00Z

Content type: article

Language: en

Sources: [GitHub Next](<https://devfeed.tech/sources/github-next.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The video explains the need for collaborative AI engineering tools and introduces Ace, a GitHub Next research prototype that brings teammates and coding agents into a shared multiplayer workspace.

### Source excerpt

Why we need collaborative AI engineering tools, and a tour of Ace -- a research prototype from GitHub Next that brings teammates and coding agents into one shared, multiplayer workspace.

## A Day in the Life as a Tech Grad (Office Edition)

DevFeed: [A Day in the Life as a Tech Grad (Office Edition)](<https://devfeed.tech/articles/a-day-in-the-life-as-a-tech-grad-office-edition-40089.md>)

Original publisher: [Read original article](<https://www.rea-group.com/about-us/news-and-insights/blog/a-day-in-the-life-as-a-tech-grad-office-edition/>)

Author: Hong Ng

Published: 2026-03-16T05:11:14Z

Content type: article

Language: en

Sources: [REA Group](<https://devfeed.tech/sources/rea-group.md>)

Topics: [Back end](<https://devfeed.tech/topics/backend.md>), [Full Stack Development](<https://devfeed.tech/topics/full-stack-development.md>), [jira](<https://devfeed.tech/topics/jira.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [back-end](<https://devfeed.tech/tags/back-end.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [entry-to-rea](<https://devfeed.tech/tags/entry-to-rea.md>), [full-stack](<https://devfeed.tech/tags/full-stack.md>), [jira](<https://devfeed.tech/tags/jira.md>), [learning](<https://devfeed.tech/tags/learning.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [team](<https://devfeed.tech/tags/team.md>), [tech](<https://devfeed.tech/tags/tech.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

A graduate engineer describes a typical office day at REA Group, including commuting, collaboration with other technology graduates, Jira planning, stand-up meetings, sprint kick-offs, and pair programming. The article also discusses learning through backend and full-stack engineering rotations.

### Source excerpt

A Day in the Life as a Tech Grad (Office Edition) Hello! I'm Hong, a graduate engineer currently working at REA Group. Before joining REA, I completed my Bachelor of Information Technology at Swinburne University of Technology. Since starting at REA, I've had the chance to work as both a back end and full-stack engineer, to contribute to real products, and to learn from engineers across two different rotations. In this blog, I'll walk through a typical day in the office as a tech grad.

## AI Coding Best Practices for Today

DevFeed: [AI Coding Best Practices for Today](<https://devfeed.tech/articles/ai-coding-best-practices-for-today-37551.md>)

Original publisher: [Read original article](<https://colintheshots.com/writing/ai-coding-best-practices-for-today/>)

Published: 2026-02-25T21:59:05Z

Content type: tutorial

Language: en

Sources: [Colin The Shots](<https://devfeed.tech/sources/colin-the-shots.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [Code](<https://devfeed.tech/topics/code.md>), [Security](<https://devfeed.tech/topics/security.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Maintainability](<https://devfeed.tech/topics/maintainability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developers](<https://devfeed.tech/tags/developers.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [llms](<https://devfeed.tech/tags/llms.md>), [maintainability](<https://devfeed.tech/tags/maintainability.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [research](<https://devfeed.tech/tags/research.md>), [uncategorized](<https://devfeed.tech/tags/uncategorized.md>)

### AI overview

A practical guide to using AI coding assistants such as GitHub Copilot, Claude, and Cursor while managing risks in code quality, deprecated APIs, security, performance, and maintainability. It emphasizes human responsibility, reviewing all generated code, and verifying it with tests, linters, and personal judgment.

### Source excerpt

Why This Document Exists AI coding assistants like GitHub Copilot, Claude, Cursor, and others can significantly accelerate development. However, research shows they also introduce systematic risks:

## Stream of Consciousness Driven Development

DevFeed: [Stream of Consciousness Driven Development](<https://devfeed.tech/articles/stream-of-consciousness-driven-development-25506.md>)

Original publisher: [Read original article](<https://buttondown.com/hillelwayne/archive/stream-of-consciousness-driven-development/>)

Author: Hillel Wayne

Published: 2026-02-18T16:33:08Z

Content type: article

Language: en

Sources: [Newsletter feed for Hillel Wayne's Newsletter](<https://devfeed.tech/sources/newsletter-feed-for-hillel-wayne-s-newsletter.md>)

Topics: [software-development](<https://devfeed.tech/topics/software-development.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>)

Tags: [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [client](<https://devfeed.tech/tags/client.md>), [computational-complexity](<https://devfeed.tech/tags/computational-complexity.md>), [development](<https://devfeed.tech/tags/development.md>), [experience](<https://devfeed.tech/tags/experience.md>), [explain](<https://devfeed.tech/tags/explain.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [partner](<https://devfeed.tech/tags/partner.md>), [question](<https://devfeed.tech/tags/question.md>), [quicksort](<https://devfeed.tech/tags/quicksort.md>), [recursion](<https://devfeed.tech/tags/recursion.md>), [solution](<https://devfeed.tech/tags/solution.md>), [sort](<https://devfeed.tech/tags/sort.md>), [spec](<https://devfeed.tech/tags/spec.md>), [want](<https://devfeed.tech/tags/want.md>)

### AI overview

When a spec change is conceptually complex, write out the reasoning together before editing the spec. The author created a Markdown file covering the problem, failed attempts, proposed solution, how it works, expected changes, and what it would not address. Questions and dead ends were added to the document as the discussion unfolded. They began changing the spec only after the client understood the reasoning and agreed with the approach. The author says this helped prevent a partner from deferring to the perceived expert and leaving behind a spec they could not maintain. The approach had been tried once and seemed promising, but requires substantial typing.

### Source excerpt

This is something I just tried out last week but it seems to have enough potential to be worth showing unpolished. I was pairing with a client on writing a spec. I saw a problem with the spec, a convoluted way of fixing the spec. Instead of trying to verbally explain it, I started by creating a new markdown file: NameOfProblem.md Then I started typing. First the problem summary, then a detailed description, then the solution and why it worked. When my partner asked questions, I incorporated his question and our discussion of it into the flow. If we hit a dead end with the solution, we marked it out as a dead end. Eventually the file looked something like this: Current state of spec Problems caused by this Elaboration of problems What we tried that didn't work Proposed Solution Theory behind proposed solution How the solution works Expected changes Other problems this helps solve Problems this does *not* help with Only once this was done, my partner fully understood the chain of thought, and we agreed it represented the right approach, did we start making changes to the spec. How is this better than just making the change? The change was conceptually complex. A rough analogy: imagine pairing with a beginner who wrote an insertion sort, and you want to replace it with quicksort. You need to explain why the insertion sort is too slow, why the quicksort isn't slow, and how quicksort actually correctly sorts a list. This could involve tangents into computational complexity, big-o notation, recursion, etc. These are all concepts you have internalized, so the change is simple to you, but the solution uses concepts the beginner does not know. So it's conceptually complex to them. I wasn't pairing with a beginning programmer or even a beginning specifier. This was a client who could confidently write complex specs on their own. But they don't work on specifications full time like I do. Any time there's a relative gap in experience in a pair, there's solutions that are concep

## AI Programming Paradigms: A Timeline

DevFeed: [AI Programming Paradigms: A Timeline](<https://devfeed.tech/articles/ai-programming-paradigms-a-timeline-25219.md>)

Original publisher: [Read original article](<https://kau.sh/blog/ai-programming/>)

Author: Kaushik Gopal

Published: 2025-07-08T00:00:00Z

Content type: article

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai-for-autocomplete](<https://devfeed.tech/tags/ai-for-autocomplete.md>), [ai-ide](<https://devfeed.tech/tags/ai-ide.md>), [ai-programming](<https://devfeed.tech/tags/ai-programming.md>), [autocomplete](<https://devfeed.tech/tags/autocomplete.md>), [chat](<https://devfeed.tech/tags/chat.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [code](<https://devfeed.tech/tags/code.md>), [code-completion](<https://devfeed.tech/tags/code-completion.md>), [coding](<https://devfeed.tech/tags/coding.md>), [commands](<https://devfeed.tech/tags/commands.md>), [context](<https://devfeed.tech/tags/context.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [ides](<https://devfeed.tech/tags/ides.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mellum](<https://devfeed.tech/tags/mellum.md>), [programming](<https://devfeed.tech/tags/programming.md>)

### AI overview

AI coding has moved from context-aware autocomplete to conversational pair programming, with agentic coding emerging as the next frontier. Super autocomplete predicts larger code blocks using surrounding code context; GitHub Copilot helped popularize it, while Cursor Tab and JetBrains Mellum represent ongoing development. Conversational coding lets developers direct an AI through chat and iterate on changes; Cursor leads this approach, but IDE lock-in is a hurdle for Android Studio and Xcode users. Firebender brings similar functionality to existing IDEs, and JetBrains offers Junie. The excerpt introduces agentic coding as able to work wherever commands can run, and characterizes it as bleeding edge; further details are not included.

### Source excerpt

A developer podcast host recently said they only use AI for autocomplete. This shocked me. That's two generations behind today's state of the art. This is how the field is evolving: I spoke about this topic in episode #301 of Fragmented. It was recorded more recently so reflects my more current thoughts on the topic. Download directly AI Programming Paradigms at a Glance Super autocomplete: AI predicts code, not just keywords. Conversational Coding: Chat with your IDE, direct the AI, iterate together. Agentic Coding: AI acts independently - runs commands, checks work, iterates. Simul Agentic? : Multiple sub-agents, parallel workflows, working together. I. Super autocomplete # This used to be one of the biggest selling points of certain IDEs like JetBrains & Visual Studio.1 The first wave of AI changed this. IDEs now predict entire classes and logic blocks, not just keywords. They excel because they feed surrounding code context to the LLM for relevant suggestions. GitHub deserves credit for kicking off the revolution with their Copilot offering. Here's an early YouTube video of mine from June 20222 showing it in action. Autocomplete keeps advancing. Cursor (today's most popular AI IDE) has "Tab". JetBrains, the pre-AI autocomplete champion, is building Mellum (an LLM built for code completion). This paradigm is alive and well, but it's become table stakes. Most developers use it, but it's far from the frontier. II - Conversational Coding # When ChatGPT took the world by storm, a new paradigm emerged. Conversational coding, where you chat with the AI and pair program together. Unlike the autocomplete era, where you trust the AI's suggestions, here you direct the AI, give it context, and nudge it toward better solutions. This is arguably what most devs use today and envision when they hear "AI programming". It feels magical, productivity jumps are real, and it's hard to think of every going backwards. Cursor leads this charge: chat with your IDE and have it make code

## AI on Technology Radar Vol.32

DevFeed: [AI on Technology Radar Vol.32](<https://devfeed.tech/articles/ai-on-technology-radar-vol-32-57332.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/machine-learning-and-ai/ai-technology-radar-vol-32>)

Author: Richard Gall

Published: 2025-04-17T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Development](<https://devfeed.tech/topics/ai-development.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [Vibe coding](<https://devfeed.tech/topics/vibe-coding.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [synthetic-data](<https://devfeed.tech/topics/synthetic-data.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistance](<https://devfeed.tech/tags/ai-assistance.md>), [ai-generated-code](<https://devfeed.tech/tags/ai-generated-code.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [llm](<https://devfeed.tech/tags/llm.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [programming](<https://devfeed.tech/tags/programming.md>), [software-development](<https://devfeed.tech/tags/software-development.md>)

### AI overview

Thoughtworks' Technology Radar discusses the growing role of AI across software, including coding assistants, software engineering agents, synthetic data and LLM applications. It highlights tools such as Cursor, Cline and Windsurf, while warning against complacency about AI-generated code and treating AI as a replacement for pair programming.

### Source excerpt

AI on Technology Radar Vol.32

## Transparency, autonomy, responsiveness, and education: How the Aha! engineering team works

DevFeed: [Transparency, autonomy, responsiveness, and education: How the Aha! engineering team works](<https://devfeed.tech/articles/transparency-autonomy-responsiveness-and-education-how-the-aha-engineering-team-works-33522.md>)

Original publisher: [Read original article](<https://www.aha.io/engineering/articles/how-we-work>)

Published: 2024-10-28T00:00:00Z

Content type: opinion

Language: en

Sources: [Aha! Engineering Blog](<https://devfeed.tech/sources/aha-engineering-blog.md>)

Topics: [Programming](<https://devfeed.tech/topics/programming.md>), [Self-organizing Team](<https://devfeed.tech/topics/self-organizing-team.md>), [Agile](<https://devfeed.tech/topics/agile.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Code](<https://devfeed.tech/topics/code.md>), [App](<https://devfeed.tech/topics/app.md>)

Tags: [agile](<https://devfeed.tech/tags/agile.md>), [approach](<https://devfeed.tech/tags/approach.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [meetings](<https://devfeed.tech/tags/meetings.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [product](<https://devfeed.tech/tags/product.md>), [programming](<https://devfeed.tech/tags/programming.md>), [security](<https://devfeed.tech/tags/security.md>), [team](<https://devfeed.tech/tags/team.md>), [teams](<https://devfeed.tech/tags/teams.md>), [transparency](<https://devfeed.tech/tags/transparency.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

The article explains how Aha!'s engineering team combines individual, pair, and team-based work. Engineers present their work in weekly meetings, retain ownership of code, and share knowledge across the organization. Small agile teams align with product areas and infrastructure, while rotating support responsibilities provide broader exposure. Product managers, designers, and engineers prioritize and scope work collaboratively.

### Source excerpt

Organizations have many different ways to approach how teammates write code. You have individual silos, pair programming, team-based work, and black box interfaces where you have no idea how the other team is structured. We use a mix of these approa

## Who Benefits Most from Cursor, Copilot, and Other AI Coding Assistants?

DevFeed: [Who Benefits Most from Cursor, Copilot, and Other AI Coding Assistants?](<https://devfeed.tech/articles/who-wins-with-cursor-copilot-33437.md>)

Original publisher: [Read original article](<https://timkellogg.me/blog/2024/08/31/llm-pairing>)

Published: 2024-08-31T00:00:00Z

Content type: opinion

Language: en

Sources: [Tim Kellogg](<https://devfeed.tech/sources/tim-kellogg.md>)

Topics: [cursor](<https://devfeed.tech/topics/cursor.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Unit testing](<https://devfeed.tech/topics/unit-testing.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [llm](<https://devfeed.tech/tags/llm.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [unit-testing](<https://devfeed.tech/tags/unit-testing.md>)

### AI overview

This opinion article argues that the benefits of AI coding assistants such as Cursor and GitHub Copilot depend less on whether a programmer is simply good or bad and more on their strengths, weaknesses, temperament, and personality. It compares these tools with unit testing and pair programming, emphasizing that AI assistants can provide broad technical knowledge, speed, and brainstorming while still making mistakes and struggling with design and innovation.

### Source excerpt

Who wins now that Cursor is out? Good programmers? Bad programmers? Here, I make the case that it is more about your tempermant and personality traits. If you're good in the places where the AI is weak, you'll knock it out of the park.

## Why test-driven development and pair programming are perfect companions for GitHub Copilot

DevFeed: [Why test-driven development and pair programming are perfect companions for GitHub Copilot](<https://devfeed.tech/articles/why-test-driven-development-and-pair-programming-are-perfect-companions-for-github-copilot-57280.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/blog/generative-ai/tdd-and-pair-programming-the-perfect-companions-for-copilot>)

Author: Juan Infante Zumer, Carlos Cavero, Carlos Barroso

Published: 2024-07-08T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Code quality](<https://devfeed.tech/topics/code-quality.md>), [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [Maintainability](<https://devfeed.tech/topics/maintainability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-for-code](<https://devfeed.tech/tags/ai-for-code.md>), [ai-smells](<https://devfeed.tech/tags/ai-smells.md>), [boost-developer-productivity](<https://devfeed.tech/tags/boost-developer-productivity.md>), [code-completion](<https://devfeed.tech/tags/code-completion.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [gen-ai](<https://devfeed.tech/tags/gen-ai.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [maintainability](<https://devfeed.tech/tags/maintainability.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [pairing](<https://devfeed.tech/tags/pairing.md>), [pitfalls](<https://devfeed.tech/tags/pitfalls.md>), [tdd](<https://devfeed.tech/tags/tdd.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

This article examines how test-driven development and pair programming can help developers use GitHub Copilot while reducing AI-related coding pitfalls. It discusses productivity and code-quality benefits, Copilot's nondeterministic suggestions, adoption and team dynamics, and risks such as automation bias, context poisoning, and missed requirements.

### Source excerpt

Why test-driven development and pair programming are perfect companions for GitHub Copilot

## Increase Engineering Productivity by 50% Through Focus and Flow

DevFeed: [Increase Engineering Productivity by 50% Through Focus and Flow](<https://devfeed.tech/articles/increase-engineering-productivity-by-50-through-focus-and-flow-39920.md>)

Original publisher: [Read original article](<https://mende.io/blog/increase-engineering-productivity-by-50-through-focus-and-flow/>)

Author: tobi@techunicorn.builders (Tobias Mende)

Published: 2024-06-01T05:00:00Z

Content type: opinion

Language: en

Sources: [Tobias Mende](<https://devfeed.tech/sources/tobias-mende.md>)

Topics: [developer-productivity](<https://devfeed.tech/topics/developer-productivity.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [context](<https://devfeed.tech/topics/context.md>), [meetings](<https://devfeed.tech/topics/meetings.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>), [real-time](<https://devfeed.tech/topics/real-time.md>)

Tags: [collaboration](<https://devfeed.tech/tags/collaboration.md>), [collaboration-communication-continuous-deployment-developer-experience-developer-productivity-e](<https://devfeed.tech/tags/collaboration-communication-continuous-deployment-developer-experience-developer-productivity-e.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [engineering-productivity](<https://devfeed.tech/tags/engineering-productivity.md>), [flow](<https://devfeed.tech/tags/flow.md>), [focus](<https://devfeed.tech/tags/focus.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [real-time](<https://devfeed.tech/tags/real-time.md>)

### AI overview

This article discusses how focus and flow affect developer productivity and presents practical organizational ideas for improving them. It emphasizes collaboration, team or pair programming, reducing distractions and context switching, real-time reviews, and useful documentation.

### Source excerpt

Increase Engineering Productivity by 50% Through Focus and Flow Creating an environment where developers can maintain focus and achieve flow can lead to a 50% increase in productivity, as research suggests. But how do we create such an environment?

## Building connections when joining a new remote team

DevFeed: [Building connections when joining a new remote team](<https://devfeed.tech/articles/building-connections-when-joining-a-new-remote-team-40803.md>)

Original publisher: [Read original article](<https://www.bloco.io/blog/building-connections-when-joining-a-new-remote-team>)

Author: Cláudia

Published: 2023-07-31T10:17:29Z

Content type: opinion

Language: en

Sources: [Bloco](<https://devfeed.tech/sources/blog-bloco.md>)

Topics: [meetings](<https://devfeed.tech/topics/meetings.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [clients](<https://devfeed.tech/tags/clients.md>), [meetings](<https://devfeed.tech/tags/meetings.md>), [mentorship](<https://devfeed.tech/tags/mentorship.md>), [onboarding](<https://devfeed.tech/tags/onboarding.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [personal-experience](<https://devfeed.tech/tags/personal-experience.md>), [remote](<https://devfeed.tech/tags/remote.md>), [slack](<https://devfeed.tech/tags/slack.md>), [team](<https://devfeed.tech/tags/team.md>), [team-culture](<https://devfeed.tech/tags/team-culture.md>), [team-dynamics](<https://devfeed.tech/tags/team-dynamics.md>)

### AI overview

A personal account of joining a remote software team, focusing on onboarding, relationship-building, team dynamics, communication preferences, pair programming, mentorship, and feedback.

### Source excerpt

Joining a new team can be a thrilling and transformative experience. Recently, I joined a new team and I want to share my personal experience about how to connect with people working remotely.

## AI-assisted programming can speed development while increasing abstraction and technical debt

DevFeed: [AI-assisted programming can speed development while increasing abstraction and technical debt](<https://devfeed.tech/articles/ai-will-be-the-high-interest-credit-card-of-2023-36663.md>)

Original publisher: [Read original article](<https://shostack.org/blog/ai-high-interest-credit-card/>)

Author: Adam

Published: 2023-06-16T00:00:00Z

Content type: opinion

Language: en

Sources: [Shostack & Friends Blog](<https://devfeed.tech/sources/shostack-friends-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Jupyter Notebook](<https://devfeed.tech/topics/jupyter-notebook.md>), [Application Security](<https://devfeed.tech/topics/application-security.md>), [Python](<https://devfeed.tech/topics/python.md>), [pair\_programming](<https://devfeed.tech/topics/pair-programming.md>), [Programming](<https://devfeed.tech/topics/programming.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [appsec](<https://devfeed.tech/tags/appsec.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [jupyter-notebooks](<https://devfeed.tech/tags/jupyter-notebooks.md>), [pair-programming](<https://devfeed.tech/tags/pair-programming.md>), [programming](<https://devfeed.tech/tags/programming.md>), [python](<https://devfeed.tech/tags/python.md>)

### AI overview

The author reflects on using ChatGPT, GitHub Copilot, pair programming, and Jupyter Notebooks while learning Python and producing graphs. The experience accelerated development and debugging, but raised concerns about code quality, application security, abstraction, and the faster accumulation of technical debt.

### Source excerpt

AI will be the high interest credit card of 2023 I haven't done a lot of work in Python, and I've never used it to produce graphs. But after an hour of pair programming and then using Chatgpt and Github Copilot got me quite far in writing a set of Jupyter Notebooks, and dramatically shrunk the effort to use and debug a new tool. I wanted to record some thoughts on the experience, and what it means for programming and for application security.

[Next page](<https://devfeed.tech/topics/pair-programming.md?cursor=WyIyMDIzLTA2LTE2VDAwOjAwOjAwKzAwOjAwIiwgIjYwNjI4MTY1LTVmNDItNGIyNC1iNTBjLTFlMWI4MDIwZjAwNyJd>)