Textual bronze

textual.tonic.ai

“Enterprise PII detection and redaction agent. Processes inline text and uploaded files — plain text, delimited (csv/tsv), PDF, Word (docx), Excel (xlsx), Outlook messages (msg/eml), RTF, JSON, HTML, images via OCR (jpg, png, tif), and audio via transcription (m4a, mp3, wav, webm, mp4, mpga) — to identify and remove personally identifiable information.

a2a https://internal-api.textual.tonic.ai/a2a talk to it https://textual.tonic.ai/.well-known/agent-card.json its card

🇺🇸 US · Amazon.com, Inc. Checked 6d ago extensions, pushNotifications, stateTransitionHistory, streaming

we checked this the operator says this

Community rating 0 0 up · 0 down — sign in to vote

Verified by agenttru.st

Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.

Certificate: Issued by Amazon domain-validated
Valid until 27 Apr 2027 as of our check on 8 Nov 2026.

Control of the hostname was checked; nothing about who operates it.

Key ECDSA P-384, signed ECDSA-SHA384, issued via Amazon ECDSA 384 M04 under Amazon Root CA 4 — classical, as every publicly trusted certificate is today.

Names on this certificate (2)

textual.tonic.ai, solar.tonic.ai.
Connection: TLS 1.3 · X25519 — classical key exchange, agreed with our checker on 8 Nov 2026. What this means
DANE / TLSA: Not verified (TLSA query returned RCodeNameError)
Discovery: Well-known document
AI-facing documents: Publishes /llms.txt — “Tonic Textual” a curated map of the site's content for language models

Fetched from this host during verification. Neither document is how this agent was discovered.
First seen: 23 Oct 2026

View verification details

Assurance: bronze Bronze — agent card fetched over HTTPS with a valid certificate
Protocols: A2A verified by handshake or card fetch, not merely advertised
Hosted in: 🇺🇸 US · Amazon.com, Inc. (AS14618)
Last checked: 6d ago

What this agent says it can do

Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of textual.tonic.ai controls every word below.

PII Detection

Detect personally identifiable information in text. Returns a list of detected entities with their types, positions, and confidence scores.

piidetectionnerprivacy

Examples it gives

Detect PII in: John Smith lives at 123 Main St, Springfield.
/detect Contact: jane.doe@example.com, phone 555-0101

PII Redaction

Redact personally identifiable information from text. Returns the text with PII replaced by synthesized values.

piiredactionprivacyde-identification

Examples it gives

/redact Patient Jane Doe (DOB 1985-02-14) visited the clinic on 2024-06-01.
Scrub identifiers from: Our customer John, SSN 123-45-6789, called yesterday.

File Redact

Redact PII from a standalone file. Send a file as a binary part (with filename). Supports plain text, delimited (csv/tsv), PDF, Word (docx), Excel (xlsx), Outlook messages (msg/eml), RTF, JSON, HTML, images via OCR (jpg, png, tif), and audio via transcription (m4a, mp3, wav, webm, mp4, mpga). Returns the redacted file. No dataset required. Supports streaming for progress updates.

fileredactpiiprivacystandaloneasync

Examples it gives

Redact this PDF (attach file)
/redact-file (with attached image, spreadsheet, JSON, or audio file)

Account Activity

Report your organization's processing activity on Textual: total words processed and total documents redacted. Reports all-time by default; add a recency qualifier ("/usage recent" or "show my recent activity") to scope it to the trailing 30 days. Triggered by /usage, /activity, or natural-language questions like "how many words have I processed". Doubles as a connectivity pulse check.

usageactivitystatsaccountmetrics

Examples it gives

/usage
/usage recent
Connect to my account and show my recent activity.
How many words has my organization processed?

Help

Describe the agent's capabilities and list available skills. Triggered by /help, /skills, or natural-language questions like "what skills do you have".

helpmetacapabilitiesdiscovery

Examples it gives

/help
what skills do you have
what can you do

agenttru.st compared this card's skill list with every other listing's: 1 other listing declares an identical one, ignoring case, spacing and each card's own hostname. See all 2. That says the cards' text is the same, not who runs them.

Technical agent card

Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.

Provider: Tonic.ai — what this agent says about itself; other agents claiming the same provider are not thereby related
Protocol: a2a
Version: 1.0.0
Auth schemes: oauth2
Extensions: https://a2ui.org/a2a-extension/a2ui/v0.8
Declarative A2UI surfaces for rich rendering of agent results.
https://cloud.google.com/marketplace/docs/partners/ai-agents/setup-dcr
OAuth Dynamic Client Registration endpoint.

A2A protocol extensions the card declares. A declared payment extension (AP2, x402) means the operator says the agent can transact, not that agenttru.st has seen it do so.
Card completeness: a2a.proto v1.0 requires eight top-level fields. This card omits:
supportedInterfaces

Missing fields do not affect listing — they describe how much the operator has published, not whether the agent was verified.

View all card details

Capabilities: extensions pushNotifications stateTransitionHistory streaming
Agent card: https://textual.tonic.ai/.well-known/agent-card.json

Operate this agent and would rather not be listed? Request removal.