--- title: "Agents — Cadenya" url: "https://cadenya.com/features/agents" description: "Connect tools, delegate to specialists, and carry memory between tasks. Try new approaches with variations, then let real feedback guide what runs next." --- ![A grove of tall trees rising from a green valley at dusk](/_astro/hero-landscape.BIJZkkKt_k8nA0.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) # Agents ## Give agents real work. Connect tools, delegate to specialists, and carry memory between tasks. Try new approaches with variations, then let real feedback guide what runs next. [Get started](https://app.cadenya.com/signup) ### Same agent. New possibilities. A variation can change the model, prompt, tools, memory, and specialist agents. Explore a different approach behind the same agent your product calls. ![](/_astro/panel-v1.DgA59z5n_1KnNMd.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Default Anthropic Claude Sonnet \[Latest\] Canary OpenAI: GPT-5.5 new variation Canary Model GPT - 5.2 Created 2 days ago Assignments - reroute shipment tool - update\_eta tool - Dispatch API tool set - Customs Broker sub-agent Memory layers Carrier Playbook - SLA Policies System prompt You are Meridian’s shipment-exceptions agent. When a delivery stalls, reroute it via the dispatch API... ### Change models. Keep the mission. Choose a different model or provider for each variation. Compare approaches while your product keeps calling the same agent. ![](/_astro/panel-v2.Bkyw06vQ_19IQw4.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Default Anthropic Claude Sonnet \[Latest\] Canary OpenAI: GPT-5.5 new variation ### Try a different toolkit. Assign tools, tool sets, sub-agents, and pools per variation. Give each approach its own capabilities and discover tools on demand. ![](/_astro/panel-v3.CgQlrOQp_1jOq8.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Enable progressive tool discovery Max tools per search 1-10 5 Search hints up to 5 delays, reroutes, customs Rerank threshold 0.0-10 \[Leave blank to skip reranking\] Tool schemas stay out of the context window until the agent asks for them — only names ride along, so every request gets smaller. ### Find the approach that works. Duplicate a variation and try a new approach. Score the outcomes to help Cadenya choose which variation handles the next objective. ![](/_astro/panel-v4.B1OHWG7t_Z1FmCGL.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) ### Feedback Search comments All sentiment All variations Created Comment Variation objective +1.00 Rerouted before the SLA breach-recipient never noticed. Canary | GPT-5.2 view objective +0.50 Caught the customs hold and updated the ETA proactively. Default | Claude Sonnet 5 view objective +0.50 Good reroute, but notified the recipient twice. Canary | GPT-5.2 view objective \-0.25 Held at facility when a reroute was available Canary | GPT-5.2 view objective +0.75 Escalated the frozen-goods lane correctly Default · Claude Sonnet 5 view objective ![](/_astro/panel-v1.DgA59z5n_1KnNMd.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Default Anthropic Claude Sonnet \[Latest\] Canary OpenAI: GPT-5.5 new variation Canary Model GPT - 5.2 Created 2 days ago Assignments - reroute shipment tool - update\_eta tool - Dispatch API tool set - Customs Broker sub-agent Memory layers Carrier Playbook - SLA Policies System prompt You are Meridian’s shipment-exceptions agent. When a delivery stalls, reroute it via the dispatch API... ![](/_astro/panel-v2.Bkyw06vQ_19IQw4.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Default Anthropic Claude Sonnet \[Latest\] Canary OpenAI: GPT-5.5 new variation ![](/_astro/panel-v3.CgQlrOQp_1jOq8.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Enable progressive tool discovery Max tools per search 1-10 5 Search hints up to 5 delays, reroutes, customs Rerank threshold 0.0-10 \[Leave blank to skip reranking\] Tool schemas stay out of the context window until the agent asks for them — only names ride along, so every request gets smaller. ![](/_astro/panel-v4.B1OHWG7t_Z1FmCGL.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) ### Feedback Search comments All sentiment All variations Created Comment Variation objective +1.00 Rerouted before the SLA breach-recipient never noticed. Canary | GPT-5.2 view objective +0.50 Caught the customs hold and updated the ETA proactively. Default | Claude Sonnet 5 view objective +0.50 Good reroute, but notified the recipient twice. Canary | GPT-5.2 view objective \-0.25 Held at facility when a reroute was available Canary | GPT-5.2 view objective +0.75 Escalated the frozen-goods lane correctly Default · Claude Sonnet 5 view objective ## There’s a webhook for that Receive webhooks for everything your agent is doing. Everything. ![A flowering bonsai on a floating island, its roots trailing below](/_astro/flowering-bonsai.DnvVrsh8_1VM3XO.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) POST /webhooks/cadenya HTTP/1.1 Host: your-app.com Content-Type: application/json { "type": "objective\_event.tool\_result", "data": { ... } } ![](/_astro/roots-code.BGowGzZb_Zy2wrd.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) ## Run your agent ``` // Template: "Track order {{ orderId }}" await cadenya.objectives.create({ agentId, firstUserMessageData: { orderId: "1234" } }); ``` ## Tag it to your customer ``` await cadenya.objectives.create({ agentId, tenant: { id: "acme" }, subject: { id: "user_123" }, firstUserMessage: "Where is my order?" }); ``` ### See where the tokens go. Track input, output, cached, and reasoning tokens over time. Filter by agent, compare models, and see token spend alongside cache hits. ![](/_astro/panel-f1.4l6oU30H_ZxiYIP.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Token consumption - Input - Cached input - Output - Reasoning ![](/_astro/token-chart.u0hUV0me.svg) 60K45K30K15K0 MonTueWedThuFriSatSun ### Results your app can work with. Define a JSON Schema for your agent’s output. Turn finished work into structured data your application can use. ![](/_astro/panel-f2.C13SfUu0_1lr3MS.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Structured output { "orderId": "1234", "status": "delayed", "action": "notify\_customer" } JSON Schema → Agent result ### See how your agent performs. Follow objectives, loops, tool calls, and feedback by agent and variation. Spot failure hotspots and see where work needs attention. ![](/_astro/panel-f3.CMkj8pLz_Z29j6CW.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Agent health VariationObjectivesLoopsTokens Default1696284K Canary1272192K ### Swap models. In one move. Map the models you use to their replacements, even across providers. Move matching agent variations together, without editing each one. ![](/_astro/panel-f4.9cC00Yel_1G92M1.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Model swap From · OpenAI GPT-4.1 To · Anthropic Claude Sonnet Perform swap ![](/_astro/panel-f1.4l6oU30H_ZxiYIP.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Token consumption - Input - Cached input - Output - Reasoning ![](/_astro/token-chart.u0hUV0me.svg) 60K45K30K15K0 MonTueWedThuFriSatSun ![](/_astro/panel-f2.C13SfUu0_1lr3MS.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Structured output { "orderId": "1234", "status": "delayed", "action": "notify\_customer" } JSON Schema → Agent result ![](/_astro/panel-f3.CMkj8pLz_Z29j6CW.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Agent health VariationObjectivesLoopsTokens Default1696284K Canary1272192K ![](/_astro/panel-f4.9cC00Yel_1G92M1.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) Model swap From · OpenAI GPT-4.1 To · Anthropic Claude Sonnet Perform swap ## Give your agent a team. 01 / Tools ### Put tools to work. Give a variation individual tools or entire tool sets. Connect the actions and systems it needs to finish the job. 02 / Sub-agents ### Call a specialist. Let an agent delegate a task to another agent. Build specialists once and put their expertise to work across your team. 03 / Agent pools ### Route the request. Group specialists into a pool. Routing instructions help choose the agent best suited to each request. ## A few things to know. What can I change between variations? The model, prompt, tools, tool sets, sub-agents, pools, memory layers, and runtime settings can all differ. How do pools choose an agent? A pool routes a request to one of its member agents using your routing instructions and the context supplied with the request. Can agents remember across tasks? Yes. Enable episodic memory and supply the same episodic key across objectives. All variations share that key’s memory layer. ![A sprawling bonsai on a floating island trailing roots](/_astro/island-tree.DSrfAQ1I_Z2pu9sW.webp?dpl=dpl_HJa8gqwfz8xwjnF1PtXneJm7pNwR) ## Put your agents to work. Start with one. Give it tools, a team, and room to grow. [Create an agent](https://app.cadenya.com/signup) [See API docs](/docs)