Frequently
Asked

Polari Technologies is a semantic intelligence infrastructure company. We build the layer between raw signal inputs — news articles, text, sensor data — and the products that need to make sense of them.

Our core product is the Polari API, a four-layer processing pipeline that converts unstructured text into structured intelligence: embeddings, entities, story clusters, and relationship graphs. Digestr is our consumer-facing news app built entirely on top of the same infrastructure.

Polari Technologies LLC is the company. The Polari API (polariapi.com) is our developer product — the intelligence layer available over HTTP. Digestr (digestr.ai) is our consumer news application. Both are built on the same underlying infrastructure.

The API is primarily built for developers and technical teams who want to add news intelligence to their own applications without spending months building semantic pipelines from scratch. Common use cases include media monitoring tools, financial intelligence platforms, research applications, and content recommendation systems.

Digestr is built for anyone who wants a smarter news reading experience — one that surfaces what's actually happening across sources, rather than just the latest headlines.

No. News is our primary use case and where we have the deepest investment, but the underlying architecture — embeddings, entity extraction, clustering, relationship graphs — applies to any text-heavy domain. The same infrastructure that clusters news articles can interpret support tickets, research papers, regulatory filings, or internal communications. If you have a use case outside of news, reach out and we'll discuss fit.

Each layer builds on the previous:

• Layer 0 — Token Intelligence. Processes raw articles through quality filtering and generates 384-dimensional semantic embeddings. This is where noise is removed and content is scored.
• Layer 1 — Semantic Analysis. Extracts named entities (people, organizations, locations, events), generates sentence-level embeddings, and adds temporal and geographic tags.
• Layer 2 — Story Clustering. Groups related articles across sources into unified story clusters using a two-stage algorithm (embedding similarity + entity overlap). 92%+ precision.
• Layer 3 — Intelligence Graph. Maps entity relationships, tracks narrative evolution, detects trends, and generates constellation graph visualization data.

Starter tier includes Layers 0–2. Layer 3 and graph access require Professional or Enterprise.

Register for an account at polariapi.com. Free trial accounts receive a key immediately with 1,000 included API calls and access to all four layers for 14 days — no credit card required. Paid tier keys are issued automatically upon subscription.

All requests authenticate via the Authorization: Bearer YOUR_API_KEY header.

English is our primary supported language with full pipeline support across all four layers. Spanish, French, German, and Chinese are on our 2026 roadmap. If your use case requires another language urgently, reach out — we may be able to discuss enterprise arrangements for specific language support.

Rate limits are enforced per API key and vary by tier:

• Starter: 1,000 requests/day, maximum 10 per minute
• Professional: 10,000 requests/day, maximum 100 per minute
• Enterprise: Custom limits with burst support

All responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers. Exceeding limits returns a 429 Too Many Requests response.

Average API response latency is under 200ms for most endpoints. Story clustering and graph queries may take up to 500ms depending on query complexity and result size. Enterprise customers have access to priority processing queues with lower tail latency.

Content freshness: articles are processed and available via the API within 5 minutes of publication from our monitored sources.

Yes, on Professional and Enterprise tiers. Webhooks allow you to subscribe to real-time events including new cluster creation, trend detection, entity mention spikes, and sentiment shifts. Professional tier supports up to 5 active webhooks; Enterprise has no limit.

See the webhook documentation for payload schemas and setup instructions.

Annual billing saves 20%. Overages are billed at $0.001 per call above your plan limit. See the full pricing page at polariapi.com/pricing.

Yes. All new accounts receive a 14-day free trial with 1,000 API calls included and access to all four layers. No credit card required to start. At the end of the trial, you can subscribe to a paid tier or your key will be deactivated.

Yes. You can cancel your subscription at any time from your account dashboard. Cancellation takes effect at the end of your current billing period — you retain full access until then. We don't offer prorated refunds for partial months, but we also don't lock you into contracts on monthly plans.

Annual plans are non-refundable except where required by applicable law.

If you exceed your plan's monthly call limit, additional requests are billed at $0.001 per call (0.1 cents). You can set a hard cap or spending alert in your account dashboard to avoid unexpected charges. Overages are invoiced at the end of the billing cycle.

Digestr is a news aggregation application powered entirely by the Polari intelligence layer. Rather than serving raw headlines, it surfaces what's actually happening: semantically clustered stories, deduplicated across sources, organized by what you care about.

It's also our primary proof of concept for the API. If something works well in Digestr, it's because the underlying Polari layer is working. The app lives at digestr.ai.

Digestr currently operates in an open beta. Core features are free. Premium features — custom topics, deeper briefing history, advanced filters — will be part of a paid tier at launch. If you're using Digestr now, you'll be grandfathered into a reasonable plan when billing goes live.

Digestr uses the Polari pipeline to cluster articles from dozens of sources into unified stories. Within each cluster, it surfaces the most informative and highest-quality articles — not just the most recent ones. Your reading patterns influence what rises to the top over time.

There are no ads in Digestr, and no advertiser influence on ranking. We don't sell your reading data.

Enterprise includes everything in Professional plus:

• Custom API call volume with burst support
• 99.9% uptime SLA
• Dedicated account manager
• Phone and Slack support
• 90-day+ data retention
• Data Processing Agreement for compliance requirements
• Opt-out from model improvement programs
• White-label deployment options
• Custom integrations on request

Enterprise pricing starts at $2,000/month. Contact sales@polaritechnologies.com to discuss your requirements.

Yes, on Enterprise agreements. White-label options allow you to deploy the Polari intelligence layer under your own brand. Custom integrations with your existing data sources, internal tools, or proprietary APIs are available as scoped projects. Pricing depends on scope — contact us to discuss.

Enterprise customers receive a 99.9% uptime SLA. Starter and Professional tiers are provided on a best-effort basis without a formal SLA guarantee, though we aim for equivalent reliability in practice. Historical uptime is published at our status page.

We use a combination of open-source and proprietary models. Embeddings are generated using sentence-transformers (all-MiniLM-L6-v2 and BAAI/bge-small-en-v1.5). Named entity recognition uses spaCy with custom fine-tuning for news domains. Clustering uses our proprietary two-stage algorithm built on top of these embeddings.

We intentionally don't rely on closed-source LLM APIs for our core pipeline — the intelligence layer needs to be fast, deterministic, and not dependent on third-party rate limits.

We currently ingest from 100+ sources via RSS feeds, direct API integrations, and web monitoring. Our source list covers major English-language publications across news, technology, finance, and policy. Enterprise customers can request specific source additions or bring their own content for processing.

For general bugs, API issues, or unexpected behavior, email hello@polaritechnologies.com or open a ticket through your account dashboard.

For security vulnerabilities, please disclose responsibly to security@polaritechnologies.com before any public disclosure. We commit to acknowledging receipt within 48 hours and resolving confirmed issues within 30 days where possible.

Python and JavaScript SDKs are on our Q1 2026 roadmap. Currently, the API is a clean REST interface that works with any HTTP client. The documentation includes code samples in Python, JavaScript, and cURL for every endpoint.