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 20,825 articles. Measured as of 26 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 — 16.8% of the lens's coverage
  • Fastest-gainingAI agents — +4.9 pp (6.5% → 11.4% of lens coverage)
  • Attention concentrationThe top 3 topics hold 37% of the coverage — broadly spread
  • Strongest pairingGoogle AI Studio + Gemini API — covered together in 63 articles · distinctiveness 0.78
What not to over-read: this measures press coverage — not adoption, revenue, or quality.
The measured read

Across the Agentic Software Development lens’s full history from July 2025 through October 2026, press attention is broad by subject but narrow by editorial mode: announcements and launch stories dominate, while recent gains are led by AI agents and extend into compact edge groupings.

Full history 40 topics 20,825 articles
  • GitHub has the largest coverage share at 16.8% but cooled by 1.1 percentage points recently, so overall prominence and current movement point in different directions.
  • Claude Code cooled by 0.8 percentage points as Copilot gained 0.5 points, so leading product coverage is not moving as a block.
  • As the press characterizes progress, announcements account for 58%, launches 33%, and results 7%, so coverage is concentrated before reported outcomes.
  • Neutral framing accounts for 88%, while promotional and critical framing take 7% and 5%, so overt evaluation sits at the margins of coverage.
  • AI agents posted the largest recent gain, rising 4.9 percentage points to 11.4%, so category-level framing is expanding most sharply.
  • Model Context Protocol holds 7.2% with steady recent coverage, so attention is not confined to organizations and named products.
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

Across 20,825 articles, launch stories account for 46% and news and updates for 39%, so launch-and-update reporting forms the editorial center. Every other story type has a single-digit share, which leaves alternative frames peripheral to that center. 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.

TopicTypeShare of coverageMovement
GitHub organization 16.8%−1.1 pp
Claude Code product 10.7%−0.8 pp
Copilot product 9%+0.5 pp
AI agents technology 7.3%+4.9 pp
Model Context Protocol technology 7.2%−0.4 pp
Codex product 6.6%+1 pp
Perplexity company 5.5%+0.3 pp
Cursor product 4.7%−0.7 pp
agentic AI technology 4.6%+0.2 pp
Claude Cowork technology 2.5%−0.2 pp
GitHub Copilot product 2.3%−0.4 pp
Moonshot AI company 2.2%+0.2 pp
Fable 5 model 2.1%−4.1 pp
Antigravity product 1.7%−0.2 pp
Google AI Studio product 1.1%steady
Z.ai company 1%+2.1 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

AI agents advanced most sharply while GitHub and Claude Code cooled, so attention is shifting within the leaders rather than simply expanding at the edges. Recent movement compares each topic’s coverage share in the latest three months with the preceding three months, treating shifts below 0.2 percentage points as steady, so it captures reallocation rather than overall scale. Z.ai and GLM-5.3 gained 2.1 and 1.6 points as Fable 5 lost 4.1, so edge attention is rotating rather than rising uniformly.

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+4.9 pp (6.5% → 11.4% of lens coverage)
  • Z.ai+2.1 pp (0.9% → 3% of lens coverage)
  • GLM-5.3+1.6 pp (0% → 1.6% of lens coverage)
  • Codex+1 pp (8.3% → 9.3% of lens coverage)
  • Cognition+0.8 pp (0.5% → 1.3% of lens coverage)
  • Copilot+0.5 pp (6% → 6.5% of lens coverage)
  • Zhipu AI+0.4 pp (0.7% → 1.1% of lens coverage)
  • Perplexity+0.3 pp (3% → 3.3% of lens coverage)
Cooling
  • Fable 5−4.1 pp (6.2% → 2.1% of lens coverage)
  • Gemini 3.5 Flash−1.4 pp (1.4% → 0% of lens coverage)
  • GPT-5.6−1.2 pp (2.4% → 1.2% of lens coverage)
  • GitHub−1.1 pp (14.8% → 13.7% of lens coverage)
  • Claude Code−0.8 pp (12.7% → 11.9% of lens coverage)
  • Cursor−0.7 pp (5.1% → 4.4% of lens coverage)
  • Model Context Protocol−0.4 pp (5.6% → 5.2% of lens coverage)
  • GitHub Copilot−0.4 pp (2.2% → 1.8% 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 16.8% Claude Code 10.7% Copilot 9% AI agents 7.3% Model Context Protocol 7.2% Codex 6.6% Perplexity 5.5% Cursor 4.7%Others 32.3%
Top-3 concentration latest month 44.4%

Broadening — across the last three measured months the top three have held 37.8% of this set's coverage, down 7.9 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)
Announcement58%
Launch33%
Results7%
Speculation2%
By press framing
Neutral88%
Promotional7%
Critical5%
Skepticalunder 1%

Story type is a share of the 12,597 classified coverage items classified on that axis; claim stage of the same number; press framing of the 12,597 whose framing could be read.

Covered together

Across the full record, Google AI Studio and Gemini API form the most strongly connected pairing; their 63 shared articles span launch and release stories. Gemini CLI broadens that grouping: it was covered with Claude Code in 81 articles and with Codex in 44, so the cluster links several named products rather than settling into one recurring duo. Agentic AI Foundation and Model Context Protocol were covered together in 36 articles, which extends the same grouping beyond product-to-product coverage.

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 ProtocolClaude CodeAgentic AI FoundationCursorGoogle AI StudioGemini APIAntigravityKiroBlockCodexA2AGitHub CopilotClaude CoworkMCP servers
Claude Code (81)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-5.3Zhipu AIZ.ai
Z.ai (32)Zhipu AI (16)GLM-5.3

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

What to watch

The compact GLM-5.3 grouping is an edge thread because its coverage gained 1.6 percentage points and Z.ai gained 2.1, while both sit with Zhipu AI in one cluster. Cognition’s coverage rose from 0.5% to 1.3%, a gain of 0.8 percentage points, so a second edge thread sits outside the established leaders. Cognition and Windsurf were covered together in 23 articles across the full record, tying that gain to an acquisition-oriented pairing rather than isolated attention.

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
AI agents technology
Model Context Protocol technology
Codex product
Perplexity company
Cursor product
agentic AI technology
Claude Cowork technology
GitHub Copilot product
Moonshot AI company
Show all 40 topics
Fable 5 model
Antigravity product
Google AI Studio product
Z.ai company
Block company
GPT-5.6 model
MCP servers technology
LangChain organization
Replit company
Gemini CLI product
n8n product
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
Agentic AI Foundation organization
Claude Managed Agents product
Agent Mode product
Representative cited sources
Show all 32 cited sources
Briefing

Coverage is broad by subject but narrow by format: announcement- and launch-led reporting dominates, AI agents coverage is gaining fastest, and the Google AI Studio–Gemini API pairing anchors the wider Gemini CLI grouping.

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