Kalcend

Kalcend lists 43 one click integrations, spanning CRM (HubSpot, Salesforce, Zoho, Capsule), helpdesk (Intercom, Zendesk, Zoho Desk) and Google Workspace (Gmail, Calendar, Drive), with Stripe and Notion named elsewhere.

Agents also read and write files, run SQL over CSVs and spreadsheets, query and write to the customer's database, and run shell commands over SSH. The Builder designs, builds and deploys custom integrations, webhook receivers and internal APIs from the chat flow, with signed webhooks. Browser automation covers systems without programmatic interfaces. Kalcend publishes no full catalog of the integrations.

Sourcekalcend.ai features and home pagesread 2026-08-31

Agents trigger and notify each other and escalate to a person when needed, and the Builder architects and assembles the agent, its tools and access from a plain-English description.

A single agent performs multi-step work including qualifying leads, scheduling meetings, updating the CRM and triggering workflows in connected tools, across an action set spanning file reads and writes, SQL over spreadsheets, database queries and writes, shell commands over SSH and browser navigation. Agents are long-running and stateful on messaging infrastructure handling delivery, retries and ordering.

Kalcend says there is no flow builder, no scripting and no separate technical workflow, and no branching, looping or conditional control-flow construct is named or inspectable.

Sourcekalcend.ai features and home pagesread 2026-08-31

Knowledge base content covers uploaded documents, URLs, text chunks and embeddings, and the platform generates answers using customer content via retrieval, with responses stored for audit and team review and not used to train third party models. The Builder generates a custom knowledge base from the customer's documents as a build step, with answers drawn from PDFs, documents and spreadsheets, and agents also run SQL over CSVs and sheets and query the customer's database directly. There is no stated chunking strategy, embedding model, reindexing or index freshness behavior.

Sourcekalcend.ai privacy policy and features pageread 2026-08-31

Agents pause for approvals, sign in and OTP and hand control to a person for anything sensitive, and when a request needs judgment the agent escalates to the customer's team on Slack or a shared inbox with the full conversation thread attached. Agents also escalate to a person when needed, alongside triggering and notifying each other. No published policy language, confidence threshold or per action approval rule defines which actions count as sensitive, so the classification appears to be the platform's, not one the customer configures.

Sourcekalcend.ai features page and home pageread 2026-08-31

Kalcend Technologies Pvt. Ltd. is data controller for account and admin data and processor for end user data, with a Data Processing Addendum applying to data processed on a customer's behalf and processing occurring only on the customer's documented instructions. Integration credentials and tokens are stored encrypted.

OpenAI and Anthropic are named as model subprocessors whose APIs are used where data is not used to train their models, responses are stored for audit and team review and not used to train third party models, and rate limiting, spam detection and incident response are in place. Special categories of data including health, biometric and financial account numbers are excluded absent a written DPA. There is no published security certification, attestation, trust page, single sign on, role based access control or retention configuration.

Sourcekalcend.ai privacy policyread 2026-08-31

Agent and automation activity is a recorded data category, covering tasks agents perform including web pages and data accessed via browser automation and connected integrations, plus workflow and webhook logs, and generated responses are stored for audit and team review. Escalation to a human attaches the full conversation thread. There is no stated reasoning trace, per step decision record, tool call detail, run inspection surface, retention period, export path or dashboard. The sandboxed playground is a testing environment used at build time.

Sourcekalcend.ai privacy policy and features pageread 2026-08-31

Memory and reminders sit among the runtime tools, holding context across turns and scheduling deferred actions up to 28 days out. Agents are long running and stateful on messaging infrastructure, and each AI employee keeps full conversation memory shared across WhatsApp, phone, Slack, web chat and email. That is conversation state carried across channels. There is no stated memory the agent writes beyond the conversation, no lifetime or purge path, and no way to review or delete what it holds.

Sourcekalcend.ai features and home pagesread 2026-09-29

Kalcend is a SaaS platform operated by an Indian incorporated company running on its own infrastructure with named subprocessors, acting as data controller for account data and processor for end user data.

There is no stated self hosting, virtual private cloud, on premises option, region selection or customer managed encryption keys, and the company's public startup registry profile describes agents built, deployed and run in a managed cloud.

The claim that enterprises can run custom models inside their own infrastructure appears only in third party directory and company profile listings, not on Kalcend's own pages.

Sourcekalcend.ai privacy policy, home and features pagesread 2026-08-31

There is no template gallery, agent catalog, role preset library or browsable prebuilt agent surface, and template and role preset examples appear only in third party directory and company profile listings.

Instead, a Builder learns the business, generates a custom knowledge base from the customer's documents and writes real integrations from a plain English description. Kalcend says explicitly that there is no flow builder, no scripting and no separate technical workflow, and it positions the product as hiring an AI employee, not assembling one from building blocks. The 43 one click integrations are connectors, not prebuilt agents.

Sourcekalcend.ai features and home pagesread 2026-08-31

Each AI employee operates across WhatsApp Business API, Slack, inbound voice calls, web chat widgets and email simultaneously out of the box. Agents trigger workflows in connected tools including HubSpot, Stripe and Notion, and agents trigger and notify each other. The Builder creates webhook receivers giving an inbound programmatic route, workflow and webhook activity is logged as a distinct processed-data category, and outbound campaigns are sent on customer instruction. There is no stated timer, cron or recurrence capability.

Sourcekalcend.ai home, features and privacy pagesread 2026-08-31

OpenAI and Anthropic are named as model subprocessors whose APIs are used where data is not used to train their models, so more than one provider powers the product under Kalcend's own selection. There is no stated model picker, bring your own key arrangement, endpoint configuration, per agent model setting or routing logic. The claim that enterprises can run custom models inside their own infrastructure appears only in third party directory and company profile listings and is not first party.

Sourcekalcend.ai privacy policy, home and features pagesread 2026-08-31

The service is a SaaS platform for building and deploying AI agents comprising knowledge bases, third party integrations, browser automation, automations and a developer API. The Builder writes real integrations with signed webhooks and builds webhook receivers and internal APIs, and webhook activity is logged as a distinct processed data category. There is no published API reference, endpoint list, authentication documentation, SDK or Model Context Protocol server, so the developer API is known only from the service description.

Sourcekalcend.ai privacy policy and features pageread 2026-08-31

The Builder tests every build in a live playground before it ships, as a step in the build sequence alongside generating the knowledge base and writing integrations, and teams simulate inputs and completions and fine tune agent behavior in a sandboxed playground before deploying. There is no stated scoring, judge, retained test set, expected outputs, run history or means of comparing one agent version against another on the same inputs.

Sourcekalcend.ai features and home pagesread 2026-08-31

Agents navigate, act and extract, operating third party web interfaces and handing off to a human for sign in or OTP. The service comprises knowledge bases, third-party integrations, browser automation, automations and a developer API, and a processed-data category covers tasks agents perform, including web pages and data accessed via browser automation. Browser automation operates alongside 43 one-click API integrations, covering systems those integrations do not reach. There is no stated desktop or operating-system control, and no statement of scope or reliability is published.

Sourcekalcend.ai features page and privacy policyread 2026-08-31