Markdown source

Coding Agents

Overview

Coding agents are AI systems that can inspect repositories, reason about requirements, edit files, run commands, test changes, and sometimes open pull requests or operate development tools. They move AI coding from autocomplete toward task execution.

Conference Context

They evolved from code completion, IDE assistants, program synthesis, CI automation, and software bots. The recent shift is tool use: agents can read context, make coordinated edits, run tests, and respond to feedback inside real development workflows.

Significance

Software work is full of local context, repetitive edits, dependency checks, and validation loops. Coding agents can compress that cycle, but only when they respect repository conventions, tests, review standards, and operational safety.

Applied Use

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Give the agent a narrow task, repository context, tests or acceptance criteria, and permission boundaries. Require it to read before editing, keep diffs scoped, run validation, report residual risk, and leave the workspace clean.

They are useful in feature slices, bug fixes, test generation, refactors, migrations, docs updates, dependency audits, and operational scripts.

Use coding agents when the task has clear acceptance criteria and the repo has enough structure to validate changes. Keep humans in the loop for architecture decisions, risky production operations, and ambiguous product calls.

Connections

Evidence Graph

Transcript-backed resources

Quote signals

Transcript-backed resources

Quote signals

Transcript-backed resources

Quote signals

Transcript-backed resources

Quote signals

Transcript-backed resources

Quote signals

Transcript-backed resources

Quote signals

This evidence graph consolidates scheduled talks, linked videos, transcripts, and slide-derived material connected to this topic.

Linked Sessions

Media Signals

Source Coverage

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| Evidence type | Count | Review note |
| --- | ---: | --- |
| other | 65 | Related pages outside the main evidence categories. |
| resources | 26 | Video/resource pages; check source status before treating as primary event evidence. |
| slides | 19 | OCR or reconstructed slide evidence; mark claims as OCR-derived unless image-reviewed. |
| talks | 24 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
| tools | 1 | Derived inventory pages; use as entity context, not independent proof. |
| transcripts | 2 | Transcript markdown; check session matching and caption quality. |

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| other | 69 | Related pages outside the main evidence categories. |
| resources | 29 | Video/resource pages; check source status before treating as primary event evidence. |
| talks | 27 | Official schedule pages; use for titles, speakers, tracks, and stated talk framing. |
| tools | 2 | Derived inventory pages; use as entity context, not independent proof. |

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| other | 70 | Related pages outside the main evidence categories. |
| resources | 33 | Video/resource pages; check source status before treating as primary event evidence. |

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| resources | 34 | Video/resource pages; check source status before treating as primary event evidence. |
| slides | 20 | OCR or reconstructed slide evidence; mark claims as OCR-derived unless image-reviewed. |

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| resources | 37 | Video/resource pages; check source status before treating as primary event evidence. |

Talks

Resources

Slides

Transcripts

Tools

This table summarizes the local evidence already linked from this topic. It is a navigation aid, not a claim that every linked page has been fully reviewed.

| resources | 39 | Video/resource pages; check source status before treating as primary event evidence. |

Talks

Resources

Slides

Transcripts

Tools

Active Use Cases

Slide-Derived Supporting Decks

These decks are slide/OCR support only; keep the article synopsis, origin, use cases, and schedule sections as the primary topic narrative.

Slide-Derived Scheduled Session Signals