diff --git a/web/public/blog/banners/scriptorium-replace-agentic-active-research-ready-intelligence.png b/web/public/blog/banners/scriptorium-replace-agentic-active-research-ready-intelligence.png new file mode 100644 index 00000000..592ea71a Binary files /dev/null and b/web/public/blog/banners/scriptorium-replace-agentic-active-research-ready-intelligence.png differ diff --git a/web/public/blog/scriptorium/chart_context.png b/web/public/blog/scriptorium/chart_context.png new file mode 100644 index 00000000..97a77178 Binary files /dev/null and b/web/public/blog/scriptorium/chart_context.png differ diff --git a/web/public/blog/scriptorium/chart_latency.png b/web/public/blog/scriptorium/chart_latency.png new file mode 100644 index 00000000..b405bb22 Binary files /dev/null and b/web/public/blog/scriptorium/chart_latency.png differ diff --git a/web/public/blog/scriptorium/chart_scale.png b/web/public/blog/scriptorium/chart_scale.png new file mode 100644 index 00000000..704ea956 Binary files /dev/null and b/web/public/blog/scriptorium/chart_scale.png differ diff --git a/web/public/blog/scriptorium/chart_tokens.png b/web/public/blog/scriptorium/chart_tokens.png new file mode 100644 index 00000000..be1a02c0 Binary files /dev/null and b/web/public/blog/scriptorium/chart_tokens.png differ diff --git a/web/src/data/blogPosts.ts b/web/src/data/blogPosts.ts index 4dc6cbce..6b54a436 100644 --- a/web/src/data/blogPosts.ts +++ b/web/src/data/blogPosts.ts @@ -10,6 +10,17 @@ export interface BlogPost { } export const blogPosts: BlogPost[] = [ + { + slug: "scriptorium-replace-agentic-active-research-ready-intelligence", + title: "Scriptorium: Replace Agentic Active Research With Ready Intelligence", + description: "Scriptorium replaces the search-fetch-filter-compress agent research loop with a continuously updated, high-signal brief — 92% fewer tokens, half the latency, identical decision quality.", + date: "Apr 2", + year: 2026, + category: "Blog", + tags: ["blog", "services", "scriptorium"], + banner: "banners/scriptorium-replace-agentic-active-research-ready-intelligence.png", + }, + { slug: "secure-network-infrastructure-ai-agents-practical-guide", title: "Secure network infrastructure for AI agents: A practical guide", diff --git a/web/src/pages/blog/scriptorium-replace-agentic-active-research-ready-intelligence.astro b/web/src/pages/blog/scriptorium-replace-agentic-active-research-ready-intelligence.astro new file mode 100644 index 00000000..abd24db4 --- /dev/null +++ b/web/src/pages/blog/scriptorium-replace-agentic-active-research-ready-intelligence.astro @@ -0,0 +1,80 @@ +--- +import BlogLayout from "../../layouts/BlogLayout.astro"; + +const bodyContent = ` +

A Network That Now Hosts Services

+

Pilot Protocol is a network built for direct, encrypted communication between autonomous AI agents. Where the current internet connects devices, Pilot Protocol connects agents — each with its own permanent identity, private channel, and a trust model that requires mutual consent before any communication happens. No central server. No middleman. No lock-in.

+

Pilot Protocol was built for agent-to-agent communication. The platform now hosts services — purpose-built intelligence providers that agents can call directly, inside the encrypted network, without touching the public internet.

+

The first production service on this infrastructure is Scriptorium.

+ +

Scriptorium

+

Scriptorium is available exclusively on Pilot Protocol — built for the agent internet, not the human one.

+

The standard pattern for an agent that needs to reason about the world: search, fetch, filter, compress, then finally think. That research loop is expensive, slow, and repeated from scratch on every call — even when the underlying reality has barely changed.

+

Scriptorium replaces that loop entirely. It continuously pulls from multiple live sources — market data, news, web search signals, and more — synthesizes everything into a high-signal brief, and serves it instantly to any agent that asks. The agent skips research and goes straight to reasoning.

+

The critical finding: agents using Scriptorium summaries perform identically to agents doing full live research on prediction markets. Same decision quality. A fraction of the cost and time.

+

Two intelligence feeds are live today.

+ +

Stock Market Intelligence

+

A continuously updated brief on the state of U.S. equity markets — price movements, unusual activity, sector trends, and relevant news — distilled into a compact summary ready for agent consumption.

+

The problem: An agent tracking market conditions has to pull signals across hundreds of companies, parse news, and make sense of the noise before it can form a single opinion. That process is slow and expensive, repeated from scratch every time.

+

The result: What would normally take thousands of data points to process arrives as a tight, high-signal brief. 92% fewer tokens. Less than half the response time.

+ +

Prediction Market Intelligence

+

A live brief on active prediction markets — current odds, momentum, and the news context driving near-term outcomes.

+

The problem: Prediction markets move on breaking information. An agent that re-gathers everything from scratch on each call is often working with stale data by the time it finishes.

+

The result: Scriptorium keeps the brief current so the agent does not have to. Validated head-to-head against agents doing full live research: identical predictive performance, with 92% fewer tokens and less than half the response time. The research was already done — the agent just had to think.

+ +

The Numbers

+

Scriptorium was benchmarked against direct data retrieval. The gap is not marginal.

+ +

Cost per Call — Token Usage per Agent Call

+ Token usage per agent call: Scriptorium vs direct retrieval +

Direct retrieval consumes 2,600 tokens before an agent produces a single word of output. Scriptorium: 210 — a 92% reduction. Total cost drops 5.9×.

+ +

Data Volume — Context Size per Agent Call

+ Context size per agent call: Scriptorium vs direct retrieval +

Direct retrieval hands an agent 10,000 characters of raw data. Scriptorium hands it 800 — 12.5× less to process, with no meaningful loss in reasoning quality.

+ +

Speed — Agent Response Latency

+ Agent response latency: Scriptorium vs direct retrieval +

Scriptorium calls complete in 1.8 seconds. Direct retrieval takes 4.5 seconds. In a multi-step agent chaining several decisions, that compounds into significant dead time.

+ +

Scale — Cumulative Token Cost at Scale

+ Cumulative token cost at scale: Scriptorium vs direct retrieval +

At 1,000 calls, direct retrieval has consumed 2.9M tokens. Scriptorium: 490K — 83% less for the same work. The gap widens linearly from there.

+ +

Why Pilot Protocol Is the Right Home for This

+

On the public internet, any data service is exposed — abuse, unauthorized access, and credential sprawl are operational realities. On Pilot Protocol, every connection is verified before it opens. There are no anonymous callers. Trust is established explicitly, not assumed.

+

There is also the question of how agents find things. On Pilot Protocol, services are discoverable by any agent on the network — no hardcoded addresses, no external directories. Scriptorium is simply available, to any agent that has established trust with it.

+

The longer bet: the agent internet builds its own service layer, separate from the human web. Pilot Protocol is the infrastructure. Scriptorium is the first proof it works.

+ +

Try It

+

Sign up at pilotprotocol.network to get your agent on the network and start calling both feeds today.

+ +

1. Start the gateway

+
sudo pilotctl gateway start --ports 8100 0:0000.0000.3814
+ +

2. Query endpoints

+

Prediction markets — today:

+
curl "http://10.4.0.1:8100/summaries/polymarket?from=2026-04-02T00:00:00Z"
+ +

Prediction markets — specific window:

+
curl "http://10.4.0.1:8100/summaries/polymarket?from=2026-04-01T00:00:00Z&to=2026-04-02T00:00:00Z"
+ +

Stock market — date shorthand:

+
curl "http://10.4.0.1:8100/summaries/stockmarket?from=2026-04-02"
+ +

Up next: How to integrate Scriptorium with agents you have already built — dropping these summaries into an existing workflow, without rewriting your architecture.

+`; +--- + + +
+ diff --git a/web/src/pages/docs/gateway.astro b/web/src/pages/docs/gateway.astro index cba6f604..462a20e0 100644 --- a/web/src/pages/docs/gateway.astro +++ b/web/src/pages/docs/gateway.astro @@ -12,6 +12,7 @@ const bodyContent = `

Gateway

  • Expose your own server on pilotprotocol network
  • Manage mappings
  • Notes & limits
  • +
  • Scriptorium: ready intelligence feeds
  • @@ -110,6 +111,28 @@ const bodyContent = `

    Gateway

    Further reading: Connect AI Agents Behind NAT Without a VPN +
    + +

    Scriptorium: ready intelligence feeds

    + +

    Scriptorium is a service hosted on Pilot Protocol that delivers continuously updated intelligence briefs — market data, prediction markets, and more — directly to your agents. No public internet exposure, no anonymous callers. Trust is established through the normal pilot handshake.

    + +

    1. Start the gateway

    +
    sudo pilotctl gateway start --ports 8100 0:0000.0000.3814
    + +

    2. Query endpoints

    + +

    Prediction markets — today:

    +
    curl "http://10.4.0.1:8100/summaries/polymarket?from=2026-04-02T00:00:00Z"
    + +

    Prediction markets — specific window:

    +
    curl "http://10.4.0.1:8100/summaries/polymarket?from=2026-04-01T00:00:00Z&to=2026-04-02T00:00:00Z"
    + +

    Stock market — date shorthand:

    +
    curl "http://10.4.0.1:8100/summaries/stockmarket?from=2026-04-02"
    + +
    + Learn more: Scriptorium: Replace Agentic Active Research With Ready Intelligence
    `; ---