Compass · Lens Report

State of Agentic Software Development

A measured view of how technology-press attention is distributed, moving and connected across 40 related topics — who holds attention, who is gaining or cooling, whether attention is concentrating or spreading out, which topics the press repeatedly connects, and what kind of coverage defines the conversation.

This is a Lens Report covering Agentic Software Development — a measurement of how the technology press covered the 40 topics in this lens, between Jul 2025 and Oct 2026, across 20,287 articles. Measured as of 14 Oct 2026. Coverage draws on at least 89 distinct outlets; the busiest single outlet accounts for about 7.8% of the set's measured press items.

New here? How to read this report

Compass reads a curated panel of technology outlets — the same panel, read at the same steady pace, month after month — and counts and classifies what the press publishes about the topics in this lens: how much attention each drew, what kinds of stories ran, which way coverage is moving, and what was covered together. Every figure below is a measurement of that coverage — never advice — and each one opens to the dated articles behind it. Read it as a coverage-landscape briefing — a measured map of the press conversation, not a ranking of the companies or technologies underneath it. The pattern is the product; the conclusions stay yours.

The read in 60 seconds
  • Most-covered topicGitHub — 16.9% of the lens's coverage
  • Fastest-gainingAI agents — +4 pp (6.4% → 10.4% of lens coverage)
  • Attention concentrationThe top 3 topics hold 37% of the coverage — broadly spread
  • Strongest pairingGoogle AI Studio + Gemini API — covered together in 62 articles · distinctiveness 0.77
What not to over-read: this measures press coverage — not adoption, revenue, or quality.
The measured read

Across Agentic Software Development coverage from July 2025 through October 2026, attention is broadly spread yet patterned because AI agents are gaining as the two largest subjects cool, while a Gemini CLI-centered set of API and protocol pairings provides the field’s clearest editorial structure.

Full history 40 topics 20,287 articles
  • GitHub leads with 16.9% of coverage but fell 1.2 percentage points when the latest three months are compared with the prior three, so the largest subject is not setting the current direction.
  • Claude Code’s share fell 1.2 percentage points while Copilot gained 0.6, so the upper tier is splitting rather than moving together.
  • AI agents rose 4 percentage points, from 6.4% to 10.4%, so the strongest recent increase is category-level rather than confined to a named product.
  • Fable 5 fell 3.9 percentage points even as Z.ai and GLM-5.3 rose 2.2 and 1.7, so their shared cluster reflects attention rotating among its members rather than moving as a bloc.
  • As the press describes it, 57% of reported work is at announcement, 34% at launch and 7% at results, so coverage foregrounds early-stage claims over reported outcomes.
  • Google AI Studio and Gemini API form the most strongly connected pairing and share 62 articles across the full record, so the field’s clearest editorial tie sits inside the Gemini CLI cluster.
What Compass measured

This report describes how the technology press covered the 40 topics in this lens over full history — which drew the most coverage, which are gaining or cooling, what's covered together, and how concentrated attention is. It measures coverage patterns, not the products themselves.

Coverage leaders

Attention in this lens is broadly spread — the three most-covered topics hold about 37% of the set’s coverage, spread across roughly 14 effective topics. Launches account for 46% and news and updates for 39% of 20,287 articles, so broad subject attention sits inside an editorial mix dominated by launches and updates. Neutral framing accounts for 88%, compared with 7% promotional and 5% critical, which is why the broad field does not read as a polarized press debate.

TopicTypeShare of coverageMovement
GitHub organization 16.9%−1.2 pp
Claude Code product 10.6%−1.2 pp
Copilot product 9.1%+0.6 pp
Model Context Protocol technology 7.3%−0.4 pp
AI agents technology 6.9%+4 pp
Codex product 6.5%+1.5 pp
Perplexity company 5.5%steady
Cursor product 4.7%−0.3 pp
agentic AI technology 4.6%steady
Claude Cowork technology 2.5%+0.2 pp
GitHub Copilot product 2.4%−0.2 pp
Fable 5 model 2.2%−3.9 pp
Moonshot AI company 2.1%+0.3 pp
Antigravity product 1.6%−0.4 pp
Google AI Studio product 1.1%steady
Canvas product 1.1%−0.8 pp

Topic share = that topic's measured articles divided by the sum of every lens topic's measured articles. An article covering several lens topics counts once for each of them, so shares measure attention to topics — not exclusive slices of unique articles. Lens entries are coverage topics, not mutually exclusive market participants — a company, its products and its models can each be topics, and their coverage overlaps. Movement is the share shift described under Momentum shifts below.

Momentum shifts

On that three-month comparison, AI agents gained 4 points, Codex added 1.5 and Copilot added 0.6, so gains extend from category framing into prominent products. GitHub and Claude Code each fell 1.2 points, while Fable 5 dropped 3.9, which is why scale and recent direction are pulling apart. Z.ai added 2.2 points, GLM-5.3 added 1.7 and Cognition added 1, so rising coverage is also collecting at the field’s edges rather than only near the top.

Movement is each topic's share of the lens's coverage in the last 3 months versus the 3 months before that, in percentage points (pp). Topics shifting less than 0.2 pp are steady.

Gaining coverage
  • AI agents+4 pp (6.4% → 10.4% of lens coverage)
  • Z.ai+2.2 pp (0.9% → 3.1% of lens coverage)
  • GLM-5.3+1.7 pp (0% → 1.7% of lens coverage)
  • Codex+1.5 pp (8.2% → 9.7% of lens coverage)
  • Cognition+1 pp (0.5% → 1.5% of lens coverage)
  • Copilot+0.6 pp (6% → 6.6% of lens coverage)
  • Zhipu AI+0.6 pp (0.7% → 1.3% of lens coverage)
  • Moonshot AI+0.3 pp (3.4% → 3.7% of lens coverage)
Cooling
  • Fable 5−3.9 pp (6.2% → 2.3% of lens coverage)
  • Gemini 3.5 Flash−1.3 pp (1.4% → 0.1% of lens coverage)
  • GitHub−1.2 pp (14.8% → 13.6% of lens coverage)
  • Claude Code−1.2 pp (12.6% → 11.4% of lens coverage)
  • GPT-5.6−1 pp (2.3% → 1.3% of lens coverage)
  • Canvas−0.8 pp (1.4% → 0.6% of lens coverage)
  • Model Context Protocol−0.4 pp (5.6% → 5.2% of lens coverage)
  • Antigravity−0.4 pp (2% → 1.6% of lens coverage)
Coverage mix over time

How the lens's coverage is divided among its topics, month by month — and how concentrated attention is across the set.

② Share of coverage over time
Each topic's share of this set's topic mentions, period by period (monthly). Absolute counts rise for everyone in a hot category, so share is what reveals whose grip is tightening or loosening. Each column sums to 100%, with the rest of the set folded into Others. One article can name several members of a set — a product family and one of its models, say — so it counts once toward each: read the bands one at a time rather than adding them together.
25%50%75%Jul 25Oct 25Jan 26Apr 26Jul 26Oct 26
GitHub 16.9% Claude Code 10.6% Copilot 9.1% Model Context Protocol 7.3% AI agents 6.9% Codex 6.5% Perplexity 5.5% Cursor 4.7%Others 32.5%
Top-3 concentration latest month 41.0%

Broadening — across the last three measured months the top three have held 36.7% of this set's coverage, down 9 points from 45.7% at the start of the window. More names are sharing the conversation.

Every value here is a dated measurement of coverage within this set, drawn from the Enginerds corpus — the same panel of sources, read at the same steady pace, month after month. It reflects how much the press writes about each topic, not revenue, adoption, or market share. The conclusion stays yours.

What the coverage is made of

Pooled across the whole lens: the kinds of stories the press runs, how far the reported work has progressed (as the press itself describes it), and the press framing.

By story type
Launch46%
News & updates39%
Benchmark4%
Partnership4%
Regulation2%
Acquisition2%
Everything else3%
By claim stage (as reported)
Announcement57%
Launch34%
Results7%
Speculation2%
By press framing
Neutral88%
Promotional7%
Critical5%
Skepticalunder 1%

Story type is a share of the 12,407 classified coverage items classified on that axis; claim stage of the same number; press framing of the 12,407 whose framing could be read.

Covered together

Judged by event-linked and cross-field reporting rather than article count alone, Google AI Studio and Gemini API are the most strongly connected pairing; they appeared together in 62 articles across the full record, so the Gemini CLI cluster has a clear internal anchor. Across that same full record, Gemini CLI appeared with Claude Code in 79 articles and with Codex in 44, which is why the cluster connects several prominent narratives rather than relying on one pair. Agentic AI Foundation and Model Context Protocol shared 33 articles across the full record, so protocol coverage is embedded in this editorial structure rather than standing apart.

Pairings are ranked by connection strength: distinctiveness weighted by how many confirmed events link the pair and how far apart the two topics sit in the field, with a company's own product-family pairs set aside. So a pair can rank above another that shows a higher raw distinctiveness score or more shared articles — each card carries both numbers. Distinctiveness is normalized co-occurrence (NPMI, −1 to 1): how much more often the pair shares stories than the two topics' separate coverage volumes alone would predict. Big topics co-occur often by volume alone; a high score means the pairing itself is the pattern. Each pairing also shows how many outlets its cited stories span: a pairing cited almost entirely by one specialist outlet is that outlet's editorial pattern, not necessarily a field-wide one. "Covered together" is a measurement of shared coverage across Compass's full measured record — not only this report's window — and not a partnership, endorsement, or equivalence.

Coverage clusters

Groups of topics the press tends to cover together — the shape of the domain's coverage neighborhoods.

Gemini CLI cluster
Gemini CLIModel Context ProtocolAgentic AI FoundationCursorGoogle AI StudioGemini APIAntigravityClaude CodeKiroBlockCodexA2AGitHub CopilotClaude Cowork
Claude Code (79)Codex (44)Cursor (43)Antigravity (24)GitHub Copilot (19)Google AI Studio (12)Gemini CLI

Line weight = articles covering the pair together (full measured record).

GLM-5.3 cluster
GLM-5.3Z.aiMoonshot AIZhipu AIFable 5
Z.ai (55)Fable 5 (49)Moonshot AI

Line weight = articles covering the pair together (full measured record).

What to watch

The GLM-5.3 cluster combines gains for Z.ai and GLM-5.3 with the sharpest cooling move, Fable 5, so attention is rotating within that editorial neighborhood rather than lifting it uniformly. Cognition gained 1 percentage point and appeared with Windsurf in 23 articles across the full record, so their acquisition-linked pairing forms a separate edge thread from the CLI/API/protocol structure.

Topics in this lens · 40

The full set this report measures, ranked by share of the lens's coverage. Topic share = that topic's measured articles divided by the sum of every lens topic's measured articles. An article covering several lens topics counts once for each of them, so shares measure attention to topics — not exclusive slices of unique articles. Lens entries are coverage topics, not mutually exclusive market participants — a company, its products and its models can each be topics, and their coverage overlaps. Share is never market share, adoption, or importance.

GitHub organization
Claude Code product
Copilot product
Model Context Protocol technology
AI agents technology
Codex product
Perplexity company
Cursor product
agentic AI technology
Claude Cowork technology
GitHub Copilot product
Fable 5 model
Show all 40 topics
Moonshot AI company
Antigravity product
Google AI Studio product
Canvas product
Z.ai company
Block company
GPT-5.6 model
LangChain organization
Gemini CLI product
n8n product
Replit company
Windsurf product
Deep Research technology
JetBrains company
Zhipu AI company
Cognition company
Gemini Spark product
Gemini API product
Kiro product
Stack Overflow organization
A2A standard
Muse Spark model
Gemini 3.5 Flash model
ChatGPT Agent product
GLM-5.3 model
Claude Managed Agents product
Agent Mode product
Agentic AI Foundation organization
Representative cited sources
Show all 32 cited sources
Briefing

Agentic software development coverage is broadly spread but patterned because recent attention is rotating toward AI-agent framing and selected edge subjects, while a Gemini CLI-centered API/protocol cluster supplies the clearest editorial structure.

Methodology

Every figure is drawn from the Enginerds corpus — a curated panel of technology outlets, each read at the same steady pace over time — and is a measurement of coverage within this lens: article counts, each topic's share of the set's coverage over time, the direction of that coverage, and which topics are covered together. Titles are shown as published; inclusion is not endorsement.

Topic share = that topic's measured articles divided by the sum of every lens topic's measured articles. An article covering several lens topics counts once for each of them, so shares measure attention to topics — not exclusive slices of unique articles. Lens entries are coverage topics, not mutually exclusive market participants — a company, its products and its models can each be topics, and their coverage overlaps.

Movement is each topic's share of the lens's coverage in the last 3 months versus the 3 months before that, in percentage points (pp). Topics shifting less than 0.2 pp are steady.

Pairings are ranked by connection strength: distinctiveness weighted by how many confirmed events link the pair and how far apart the two topics sit in the field, with a company's own product-family pairs set aside. So a pair can rank above another that shows a higher raw distinctiveness score or more shared articles — each card carries both numbers. Distinctiveness is normalized co-occurrence (NPMI, −1 to 1): how much more often the pair shares stories than the two topics' separate coverage volumes alone would predict. Big topics co-occur often by volume alone; a high score means the pairing itself is the pattern.

What this report does not claim. Compass measures coverage patterns in the technology press. It does not predict outcomes, rank technologies by merit or importance, or recommend what to buy, build, or invest in. Coverage is not the same as real-world significance.

Track this lens live in Compass.

This is a sample of the State of X report Compass generates over any lens or topic set. Explore the lens interactively, or generate your own reports with a Pro plan.

Explore this lens → Download PDF See Compass plans What is Compass?
Built on a curated technology press corpus

Compass measures a dated, source-linked corpus of technology coverage — a curated panel of 140+ sources, each read at the same steady pace, month after month. Most are established outlets and specialist publications. The rest are channels that companies and projects run themselves, and those are counted separately. Every measurement opens back to the cited articles behind it.

View the corpus methodology →
Compass
🔭 Lenses — curated starting points/compass/lenses🧭 Landscape — what changed/compass/landscape📊 Boards — velocity / emergence / divergence/compass/boards⚖ Compare/compass/compare⇄ Connections/compass/bridges🕸 Relationship Map — my saved maps/compass/ontology📌 Watchlist & Alerts/compass/watchlist🗺 The Signal Map/compass/signal-map📚 Topics/compass/forces🔌 API keys & Feed/compass/api-keys
↑ ↓ navigate ↵ open esc close